{
"openapi": "3.1.0",
"info": {
"title": "AssemblyAI API",
"description": "AssemblyAI API",
"version": "1.3.4",
"termsOfService": "https://www.assemblyai.com/legal/terms-of-service",
"contact": {
"name": "API Support",
"email": "support@assemblyai.com",
"url": "https://www.assemblyai.com/docs/"
}
},
"servers": [
{
"url": "https://api.assemblyai.com",
"description": "AssemblyAI API",
"x-fern-server-name": "Default"
}
],
"tags": [
{
"name": "transcript",
"description": "Transcript related operations",
"externalDocs": {
"url": "https://www.assemblyai.com/docs/guides/transcribing-an-audio-file"
}
},
{
"name": "streaming",
"description": "Streaming Speech-to-Text",
"externalDocs": {
"url": "https://www.assemblyai.com/docs/streaming/select-the-speech-model"
}
}
],
"security": [
{
"ApiKey": []
}
],
"paths": {
"/v2/upload": {
"post": {
"tags": [
"transcript"
],
"summary": "Upload a media file",
"description": "\nUpload a media file to AssemblyAI's servers.\n\nTo upload a media file to our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nRequests to transcribe uploaded files must use an API key from the same project as the key that was used to upload the file. If you use an API key from a different project you will get a `403` error and \"Cannot access uploaded file\" message.\n",
"operationId": "uploadFile",
"x-fern-sdk-group-name": "files",
"x-fern-sdk-method-name": "upload",
"requestBody": {
"content": {
"application/octet-stream": {
"schema": {
"type": "string",
"format": "binary"
}
}
}
},
"responses": {
"200": {
"x-label": "Media file uploaded",
"description": "Media file uploaded successfully",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/UploadedFile"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"403": {
"$ref": "#/components/responses/CannotAccessUploadedFile"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"422": {
"x-label": "Upload failed",
"description": "Upload failed (for example, when the request body is empty). The response body is plain text, not JSON.\n",
"content": {
"text/plain": {
"schema": {
"type": "string"
},
"example": "Upload failed, please try again. If you continue to have issues please reach out to support@assemblyai.com"
}
}
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript": {
"post": {
"tags": [
"transcript"
],
"summary": "Transcribe audio",
"description": "\nTo use our EU server for transcription, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nBuilding a load test or submitting a large batch? [See our guide \u2192](/pre-recorded-audio/guides/bulk-transcription-and-load-tests-at-scale)\nCreate a transcript from a media file that is accessible via a URL.\n",
"operationId": "createTranscript",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "submit",
"x-fern-request-name": "TranscriptParams",
"requestBody": {
"description": "Params to create a transcript",
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/TranscriptParams"
}
}
}
},
"responses": {
"200": {
"x-label": "Transcript created",
"description": "Transcript created and queued for processing",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Transcript"
},
"example": {
"id": "0072a82b-aa22-4962-add2-6121c36c17c6",
"language_model": "assemblyai_default",
"acoustic_model": "assemblyai_default",
"language_code": null,
"speech_understanding": null,
"translated_texts": null,
"status": "processing",
"audio_url": "https://assembly.ai/wildfires.mp3",
"text": null,
"words": null,
"utterances": null,
"confidence": null,
"audio_duration": null,
"punctuate": true,
"format_text": true,
"dual_channel": false,
"webhook_url": null,
"webhook_status_code": null,
"webhook_auth": false,
"webhook_auth_header_name": null,
"speed_boost": false,
"auto_highlights_result": null,
"auto_highlights": true,
"audio_start_from": null,
"audio_end_at": null,
"word_boost": [],
"boost_param": null,
"prompt": null,
"keyterms_prompt": null,
"filter_profanity": true,
"redact_pii": false,
"redact_pii_audio": false,
"redact_pii_audio_quality": null,
"redact_pii_audio_options": null,
"redact_pii_policies": null,
"redact_pii_sub": null,
"redact_static_entities": null,
"speaker_labels": true,
"speaker_options": {
"min_speakers_expected": 2,
"max_speakers_expected": 2,
"advanced_speaker_segmentation": true
},
"content_safety": true,
"iab_categories": true,
"content_safety_labels": {},
"iab_categories_result": {},
"language_detection": true,
"language_detection_options": null,
"language_detection_results": null,
"language_confidence_threshold": 0.7,
"language_confidence": null,
"custom_spelling": null,
"throttled": false,
"auto_chapters": false,
"summarization": false,
"summary_type": null,
"summary_model": null,
"custom_topics": false,
"topics": [],
"speech_threshold": null,
"speech_model": null,
"speech_models": [
"universal-3-pro",
"universal-2"
],
"speech_model_used": null,
"temperature": null,
"remove_audio_tags": "all",
"chapters": null,
"disfluencies": false,
"entity_detection": true,
"sentiment_analysis": true,
"sentiment_analysis_results": null,
"entities": null,
"speakers_expected": 2,
"summary": null,
"custom_topics_results": null,
"is_deleted": null,
"multichannel": null,
"project_id": 14296,
"token_id": 14296
}
}
},
"links": {
"GetTranscriptById": {
"$ref": "#/components/links/GetTranscriptById"
},
"GetTranscriptSentencesById": {
"$ref": "#/components/links/GetTranscriptSentencesById"
},
"GetTranscriptParagraphsById": {
"$ref": "#/components/links/GetTranscriptParagraphsById"
},
"GetTranscriptSubtitlesById": {
"$ref": "#/components/links/GetTranscriptSubtitlesById"
},
"GetTranscriptRedactedAudioById": {
"$ref": "#/components/links/GetTranscriptRedactedAudioById"
},
"WordSearchByTranscriptId": {
"$ref": "#/components/links/WordSearchByTranscriptId"
},
"DeleteTranscriptById": {
"$ref": "#/components/links/DeleteTranscriptById"
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
},
"callbacks": {
"transcriptReadyWebhook": {
"{$request.body#/webhook_url}": {
"post": {
"summary": "Transcript ready webhook",
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/TranscriptReadyNotification"
}
}
}
},
"responses": {
"2XX": {
"description": "Successfully received the notification"
},
"4XX": {
"description": "Invalid request"
},
"5XX": {
"description": "Unexpected error"
}
}
}
}
},
"redactedAudioWebhook": {
"{$request.body#/webhook_url}": {
"post": {
"summary": "Redacted audio ready webhook",
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/RedactedAudioNotification"
}
}
}
},
"responses": {
"2XX": {
"description": "Successfully received the notification"
},
"4XX": {
"description": "Invalid request"
},
"5XX": {
"description": "Unexpected error"
}
}
}
}
}
}
},
"get": {
"tags": [
"transcript"
],
"summary": "List transcripts",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "list",
"x-fern-request-name": "ListTranscriptParams",
"operationId": "listTranscripts",
"description": "\nTo retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nRetrieve a list of transcripts you created.\nTranscripts are sorted from newest to oldest and can be retrieved for the last 90 days of usage. The previous URL always points to a page with older transcripts.\n\nIf you need to retrieve transcripts from more than 90 days ago please reach out to our Support team at support@assemblyai.com.\n\n**Pagination**\n\nThis endpoint returns paginated results. The response includes a `page_details` object with the following properties:\n- `page_details.limit` - Maximum number of transcripts per page.\n- `page_details.result_count` - Total number of transcripts returned on the current page.\n- `page_details.current_url` - URL to the current page.\n- `page_details.prev_url` - URL to the previous page of older transcripts.\n- `page_details.next_url` - URL to the next page of newer transcripts.\n",
"parameters": [
{
"name": "limit",
"x-label": "Limit",
"in": "query",
"description": "Maximum amount of transcripts to retrieve",
"schema": {
"type": "integer",
"minimum": 1,
"maximum": 200,
"default": 10
}
},
{
"name": "status",
"x-label": "Status",
"in": "query",
"description": "Filter by transcript status",
"schema": {
"$ref": "#/components/schemas/TranscriptStatus"
}
},
{
"name": "created_on",
"x-label": "Created on",
"in": "query",
"description": "Only get transcripts created on this date",
"schema": {
"type": "string",
"format": "date"
}
},
{
"name": "before_id",
"x-label": "Before ID",
"in": "query",
"description": "Get transcripts that were created before this transcript ID",
"schema": {
"type": "string",
"format": "uuid"
}
},
{
"name": "after_id",
"x-label": "After ID",
"in": "query",
"description": "Get transcripts that were created after this transcript ID",
"schema": {
"type": "string",
"format": "uuid"
}
},
{
"name": "throttled_only",
"x-label": "Throttled only",
"in": "query",
"description": "Only get throttled transcripts, overrides the status filter",
"schema": {
"type": "boolean",
"default": false
},
"deprecated": true
}
],
"responses": {
"200": {
"description": "A list of transcripts. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.\n",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/TranscriptList"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript/{transcript_id}": {
"get": {
"tags": [
"transcript"
],
"summary": "Get transcript",
"operationId": "getTranscript",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "get",
"x-fern-request-name": "GetTranscriptParams",
"description": "\nTo retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nGet the transcript resource. The transcript is ready when the \"status\" is \"completed\".\n",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "The transcript resource",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Transcript"
}
}
},
"links": {
"GetTranscriptById": {
"$ref": "#/components/links/GetTranscriptById"
},
"GetTranscriptSentencesById": {
"$ref": "#/components/links/GetTranscriptSentencesById"
},
"GetTranscriptParagraphsById": {
"$ref": "#/components/links/GetTranscriptParagraphsById"
},
"GetTranscriptSubtitlesById": {
"$ref": "#/components/links/GetTranscriptSubtitlesById"
},
"GetTranscriptRedactedAudioById": {
"$ref": "#/components/links/GetTranscriptRedactedAudioById"
},
"WordSearchByTranscriptId": {
"$ref": "#/components/links/WordSearchByTranscriptId"
},
"DeleteTranscriptById": {
"$ref": "#/components/links/DeleteTranscriptById"
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
},
"delete": {
"tags": [
"transcript"
],
"summary": "Delete transcript",
"description": "\nTo delete your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nRemove the data from the transcript and mark it as deleted.\nFiles uploaded via the `/upload` endpoint are immediately deleted alongside the transcript when you make a DELETE request, ensuring your data is removed from our systems right away.\n",
"operationId": "deleteTranscript",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "delete",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "The deleted transcript response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Transcript"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript/{transcript_id}/{subtitle_format}": {
"get": {
"tags": [
"transcript"
],
"summary": "Get subtitles for transcript",
"description": "\nTo retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nExport your transcript in SRT or VTT format to use with a video player for subtitles and closed captions.\n",
"operationId": "getSubtitles",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "getSubtitles",
"x-fern-request-name": "GetSubtitlesParams",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
},
{
"name": "subtitle_format",
"x-label": "Subtitle format",
"in": "path",
"description": "The format of the captions",
"required": true,
"schema": {
"$ref": "#/components/schemas/SubtitleFormat"
}
},
{
"name": "chars_per_caption",
"x-label": "Number of characters per caption",
"in": "query",
"description": "The maximum number of characters per caption",
"schema": {
"type": "integer"
}
}
],
"responses": {
"200": {
"description": "The exported captions as text",
"content": {
"text/plain": {
"schema": {
"type": "string",
"example": "WEBVTT\n00:12.340 --> 00:16.220\nLast year I showed these two slides said that demonstrate\n00:16.200 --> 00:20.040\nthat the Arctic ice cap which for most of the last 3,000,000 years has been the\n00:20.020 --> 00:25.040\nsize of the lower 48 States has shrunk by 40% but this understates\n"
},
"examples": {
"srt": {
"$ref": "#/components/examples/SrtSubtitlesResponse"
},
"vtt": {
"$ref": "#/components/examples/VttSubtitlesResponse"
}
}
},
"text/html": {
"schema": {
"type": "string",
"example": "WEBVTT\n00:12.340 --> 00:16.220\nLast year I showed these two slides said that demonstrate\n00:16.200 --> 00:20.040\nthat the Arctic ice cap which for most of the last 3,000,000 years has been the\n00:20.020 --> 00:25.040\nsize of the lower 48 States has shrunk by 40% but this understates\n"
},
"examples": {
"srt": {
"$ref": "#/components/examples/SrtSubtitlesResponse"
},
"vtt": {
"$ref": "#/components/examples/VttSubtitlesResponse"
}
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"x-label": "Not found",
"description": "Returned when `subtitle_format` is not `srt` or `vtt`. The response body is a plain HTML 404 page \u2014 the literal string `404: Not Found` \u2014 not JSON. Unknown `transcript_id` lookups, by contrast, return a `400` with a JSON `Error` object.\n",
"content": {
"text/html": {
"schema": {
"type": "string"
},
"example": "404: Not Found"
}
}
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript/{transcript_id}/sentences": {
"get": {
"tags": [
"transcript"
],
"summary": "Get sentences in transcript",
"operationId": "getTranscriptSentences",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "getSentences",
"x-fern-request-name": "GetSentencesParams",
"description": "\nTo retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nGet the transcript split by sentences. The API will attempt to semantically segment the transcript into sentences to create more reader-friendly transcripts.\n",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "Exported sentences",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SentencesResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript/{transcript_id}/paragraphs": {
"get": {
"tags": [
"transcript"
],
"summary": "Get paragraphs in transcript",
"operationId": "getTranscriptParagraphs",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "getParagraphs",
"x-fern-request-name": "GetParagraphsParams",
"description": "\nTo retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nGet the transcript split by paragraphs. The API will attempt to semantically segment your transcript into paragraphs to create more reader-friendly transcripts.\n",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "Exported paragraphs",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ParagraphsResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript/{transcript_id}/word-search": {
"get": {
"tags": [
"transcript"
],
"summary": "Search words in transcript",
"description": "\nTo search through a transcription created on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.\nSearch through the transcript for keywords. You can search for individual words, numbers, or phrases containing up to five words or numbers.\n",
"operationId": "wordSearch",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "wordSearch",
"x-fern-request-name": "WordSearchParams",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
},
{
"name": "words",
"x-label": "Words",
"in": "query",
"description": "Keywords to search for",
"required": true,
"style": "form",
"explode": false,
"schema": {
"type": "array",
"items": {
"x-label": "Word",
"type": "string"
}
}
}
],
"responses": {
"200": {
"description": "Word search response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/WordSearchResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
},
"/v2/transcript/{transcript_id}/redacted-audio": {
"get": {
"tags": [
"transcript"
],
"summary": "Get redacted audio",
"description": "\nTo retrieve the redacted audio on the EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com` in the `GET` request above.\nRedacted audio files are only available for 24 hours. Make sure to download the file within this time frame.\nRetrieve the redacted audio object containing the status and URL to the redacted audio.\n",
"operationId": "getRedactedAudio",
"x-fern-sdk-group-name": "transcripts",
"x-fern-sdk-method-name": "getRedactedAudio",
"x-fern-request-name": "GetRedactedAudioParams",
"parameters": [
{
"name": "transcript_id",
"x-label": "Transcript ID",
"in": "path",
"description": "ID of the transcript",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "The redacted audio object containing the status and URL to the redacted audio",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/RedactedAudioResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest"
},
"401": {
"$ref": "#/components/responses/Unauthorized"
},
"404": {
"$ref": "#/components/responses/NotFound"
},
"429": {
"$ref": "#/components/responses/TooManyRequests"
},
"500": {
"$ref": "#/components/responses/InternalServerError"
},
"503": {
"$ref": "#/components/responses/ServiceUnavailable"
},
"504": {
"$ref": "#/components/responses/GatewayTimeout"
}
}
}
}
},
"components": {
"links": {
"GetTranscriptById": {
"operationId": "getTranscript",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `GET /v2/transcript/{transcript_id}`."
},
"GetTranscriptSentencesById": {
"operationId": "getSentences",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `GET /v2/transcript/{transcript_id}/sentences`."
},
"GetTranscriptParagraphsById": {
"operationId": "getParagraphs",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `GET /v2/transcript/{transcript_id}/paragraphs`."
},
"GetTranscriptSubtitlesById": {
"operationId": "getSubtitles",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `GET /v2/transcript/{transcript_id}/{subtitle_format}`."
},
"GetTranscriptRedactedAudioById": {
"operationId": "getRedactedAudio",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `GET /v2/transcript/{transcript_id}/redacted-audio`."
},
"WordSearchByTranscriptId": {
"operationId": "wordSearch",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `GET /v2/transcript/{transcript_id}/word-search`."
},
"DeleteTranscriptById": {
"operationId": "deleteTranscript",
"parameters": {
"transcript_id": "$response.body#/id"
},
"description": "The transcript ID can be used as the `transcript_id` parameter in `DELETE /v2/transcript/{transcript_id}`."
}
},
"schemas": {
"TranscriptReadyNotification": {
"description": "The notification when the transcript status is completed or error.",
"x-label": "Transcript ready notification",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"properties": {
"transcript_id": {
"x-label": "Transcript ID",
"description": "The ID of the transcript",
"type": "string",
"format": "uuid"
},
"status": {
"x-label": "Transcript status",
"description": "The status of the transcript. Either completed or error.",
"$ref": "#/components/schemas/TranscriptReadyStatus"
}
},
"required": [
"transcript_id",
"status"
],
"example": {
"transcript_id": "9ea68fd3-f953-42c1-9742-976c447fb463",
"status": "completed"
}
},
"RedactedAudioNotification": {
"description": "The notification when the redacted audio is ready.",
"x-label": "Redacted audio notification",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"allOf": [
{
"$ref": "#/components/schemas/RedactedAudioResponse"
}
]
},
"RedactedAudioResponse": {
"type": "object",
"additionalProperties": false,
"x-label": "Redacted audio response",
"x-fern-sdk-group-name": "transcripts",
"required": [
"status",
"redacted_audio_url"
],
"properties": {
"status": {
"x-label": "Status",
"description": "The status of the redacted audio",
"$ref": "#/components/schemas/RedactedAudioStatus"
},
"redacted_audio_url": {
"x-label": "Redacted audio URL",
"description": "The URL of the redacted audio file",
"type": "string",
"format": "url"
}
},
"example": {
"redacted_audio_url": "https://s3.us-west-2.amazonaws.com/api.assembly.ai.usw2/redacted-audio/785efd9e-0e20-45e1-967b-3db17770ed9f.wav?AWSAccessKeyId=aws-access-key0id&Signature=signature&x-amz-security-token=security-token&Expires=1698966551",
"status": "redacted_audio_ready"
}
},
"RedactedAudioStatus": {
"x-label": "Redacted audio status",
"description": "The status of the redacted audio",
"x-fern-sdk-group-name": "transcripts",
"type": "string",
"enum": [
"redacted_audio_ready"
],
"x-aai-enum": {
"redacted_audio_ready": {
"label": "Redacted audio is ready"
}
}
},
"SubtitleFormat": {
"x-label": "Subtitle format",
"description": "Format of the subtitles",
"x-fern-sdk-group-name": "transcripts",
"type": "string",
"enum": [
"srt",
"vtt"
],
"x-aai-enum": {
"srt": {
"label": "SRT"
},
"vtt": {
"label": "VTT"
}
}
},
"WordSearchResponse": {
"x-label": "Word search response",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"properties": {
"id": {
"x-label": "Transcript ID",
"description": "The ID of the transcript",
"type": "string",
"format": "uuid"
},
"total_count": {
"x-label": "Total count of matches",
"description": "The total count of all matched instances. For e.g., word 1 matched 2 times, and word 2 matched 3 times, `total_count` will equal 5.",
"type": "integer"
},
"matches": {
"x-label": "Matches",
"description": "The matches of the search",
"type": "array",
"items": {
"x-label": "Match",
"$ref": "#/components/schemas/WordSearchMatch"
}
}
},
"required": [
"id",
"total_count",
"matches"
],
"example": {
"id": "d5a3d302-066e-43fb-b63b-8f57baf185db",
"total_count": 10,
"matches": [
{
"text": "smoke",
"count": 6,
"timestamps": [
[
250,
650
],
[
49168,
49398
],
[
55284,
55594
],
[
168888,
169118
],
[
215108,
215386
],
[
225944,
226170
]
],
"indexes": [
0,
136,
156,
486,
652,
698
]
},
{
"text": "wildfires",
"count": 4,
"timestamps": [
[
1668,
2346
],
[
33852,
34546
],
[
50118,
51110
],
[
231356,
232354
]
],
"indexes": [
4,
90,
140,
716
]
}
]
}
},
"WordSearchMatch": {
"type": "object",
"x-label": "Word search match",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"properties": {
"text": {
"x-label": "Text",
"description": "The matched word",
"type": "string"
},
"count": {
"x-label": "Count",
"description": "The total amount of times the word is in the transcript",
"type": "integer"
},
"timestamps": {
"x-label": "Timestamps",
"description": "An array of timestamps",
"type": "array",
"items": {
"x-label": "Timestamp",
"$ref": "#/components/schemas/WordSearchTimestamp"
}
},
"indexes": {
"x-label": "Indexes",
"description": "An array of all index locations for that word within the `words` array of the completed transcript",
"type": "array",
"items": {
"x-label": "Index",
"type": "integer"
}
}
},
"required": [
"text",
"count",
"timestamps",
"indexes"
],
"example": {
"text": "smoke",
"count": 6,
"timestamps": [
[
250,
650
],
[
49168,
49398
],
[
55284,
55594
],
[
168888,
169118
],
[
215108,
215386
],
[
225944,
226170
]
],
"indexes": [
0,
136,
156,
486,
652,
698
]
}
},
"WordSearchTimestamp": {
"x-label": "Word search timestamp",
"description": "An array of timestamps structured as [`start_time`, `end_time`] in milliseconds",
"x-fern-sdk-group-name": "transcripts",
"type": "array",
"items": {
"x-label": "Timestamp",
"description": "Timestamp in milliseconds",
"type": "integer"
},
"example": [
250,
650
]
},
"Timestamp": {
"x-label": "Timestamp",
"description": "Timestamp containing a start and end property in milliseconds",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"properties": {
"start": {
"x-label": "Start",
"description": "The start time in milliseconds",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The end time in milliseconds",
"type": "integer"
}
},
"required": [
"start",
"end"
],
"example": {
"start": 3978,
"end": 5114
}
},
"TranscriptOptionalParams": {
"x-label": "Optional transcript parameters",
"description": "The parameters for creating a transcript",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"properties": {
"audio_end_at": {
"x-label": "Audio end at",
"description": "The point in time, in milliseconds, to stop transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.",
"type": "integer"
},
"audio_start_from": {
"x-label": "Audio start from",
"description": "The point in time, in milliseconds, to begin transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.",
"type": "integer"
},
"auto_chapters": {
"x-label": "Auto chapters",
"description": "Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters), can be true or false. Requires `punctuate` to be `true`, and cannot be enabled together with `summarization`. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n",
"type": "boolean",
"default": false,
"deprecated": true
},
"auto_highlights": {
"x-label": "Key phrases",
"description": "Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases), either true or false",
"type": "boolean",
"default": false
},
"content_safety": {
"x-label": "Content Moderation",
"description": "Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false",
"type": "boolean",
"default": false
},
"content_safety_confidence": {
"x-label": "Content Moderation confidence",
"description": "The confidence threshold for the [Content Moderation](https://www.assemblyai.com/docs/content-moderation) model. Values must be between 25 and 100. Requires `content_safety` to be enabled; otherwise it's ignored.",
"type": "integer",
"default": 50,
"minimum": 25,
"maximum": 100
},
"custom_spelling": {
"x-label": "Custom spellings",
"description": "Customize how words are spelled and formatted using to and from values. Each `to` value must be a single word, and each `from` phrase can contain at most 5 words. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details.",
"type": "array",
"items": {
"x-label": "Custom spelling",
"$ref": "#/components/schemas/TranscriptCustomSpelling"
}
},
"disfluencies": {
"x-label": "Disfluencies",
"description": "Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like \"umm\", in your media file; can be true or false. Supported on Universal-3.5 Pro and Universal-2.",
"type": "boolean",
"default": false
},
"domain": {
"x-label": "Domain",
"description": "Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `\"medical-v1\"` to enable [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages.\n\nSupported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If `medical-v1` is used with an unsupported language, the parameter is ignored and a warning is returned.\n",
"type": [
"string",
"null"
],
"enum": [
"medical-v1",
null
],
"default": null
},
"entity_detection": {
"x-label": "Entity Detection",
"description": "Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection), can be true or false",
"type": "boolean",
"default": false
},
"filter_profanity": {
"x-label": "Filter profanity",
"description": "Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details.",
"type": "boolean",
"default": false
},
"format_text": {
"x-label": "Format text",
"description": "Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false",
"type": "boolean",
"default": true
},
"iab_categories": {
"x-label": "Topic Detection",
"description": "Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection), can be true or false",
"type": "boolean",
"default": false
},
"keyterms_prompt": {
"x-label": "Keyterms prompt",
"description": "Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3.5 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro/prompting#keyterms-prompting) for more details.\n",
"type": "array",
"items": {
"x-label": "Keyterm",
"type": "string"
}
},
"language_code": {
"x-label": "Language code",
"description": "The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nIf you don't specify a language, it's detected automatically. Cannot be used together with `language_detection`.\n",
"oneOf": [
{
"anyOf": [
{
"$ref": "#/components/schemas/TranscriptLanguageCode"
},
{
"type": "string"
}
]
},
{
"type": "null"
}
],
"x-ts-type": "LiteralUnion | null",
"x-go-type": "TranscriptLanguageCode"
},
"language_codes": {
"description": "The language codes of your audio file. Used for [Code switching](/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Language code",
"$ref": "#/components/schemas/TranscriptLanguageCode"
}
},
"language_confidence_threshold": {
"x-label": "Language confidence threshold",
"description": "The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nDefaults to 0. Can only be set when `language_detection` is enabled. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "number",
"format": "float",
"minimum": 0,
"maximum": 1,
"default": 0
},
"language_detection": {
"x-label": "Language detection",
"description": "[Automatic language detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) identifies the spoken language and routes the request to the best model. It's applied automatically when you don't specify a `language_code`. Set to `false` only together with a `language_code`; disabling it without specifying a language returns an error.",
"type": "boolean"
},
"language_detection_options": {
"x-label": "Specify options for Automatic Language Detection.",
"description": "Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection).",
"type": "object",
"additionalProperties": false,
"properties": {
"expected_languages": {
"x-label": "Expected languages",
"description": "List of languages expected in the audio file. Defaults to `[\"all\"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.",
"type": "array",
"items": {
"x-label": "language",
"type": "string"
}
},
"fallback_language": {
"x-label": "Fallback language",
"description": "If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `[\"auto\"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "string",
"default": "auto"
},
"code_switching": {
"x-label": "Code switching",
"description": "Whether [code switching](/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n",
"type": "boolean",
"default": false
},
"code_switching_confidence_threshold": {
"x-label": "Code switching confidence threshold",
"description": "The confidence threshold for [code switching](/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n",
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.3
},
"localization": {
"x-label": "Localization",
"description": "Render the transcript in a regional variant of the detected language. Supported values are `en_au` (Australian English) and `en_uk` (British English) — only English is supported today, and you can specify at most one locale per base language. Base or default-region codes such as `en` and `en_us` are not localization variants and return a `400`.\n\nWhen the detected language matches the requested locale's base language, the transcript uses that locale's spelling and `language_code` returns the region-aware code (for example `en_au`) instead of the base `en`. Otherwise, when the detected language isn't available as a locale, the option is ignored. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "array",
"items": {
"x-label": "locale",
"type": "string"
}
},
"on_no_speech_detected": {
"x-label": "On no speech detected",
"description": "Controls what happens when no speech is detected in the audio. With `error` (the default), the transcript fails and the reason is returned in `error`. With `fallback`, the transcript completes with an empty `text`, `language_code` is set to the `fallback_language`, and an explanatory warning is returned in `metadata.warnings`.\n\n`fallback` requires `fallback_language` to be set to a specific language code; `auto` returns a `400`. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "string",
"enum": [
"error",
"fallback"
],
"default": "error"
}
}
},
"multichannel": {
"x-label": "Multichannel",
"description": "Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) transcription, can be true or false.",
"type": "boolean",
"default": false
},
"prompt": {
"x-label": "Prompt",
"description": "Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3.5 Pro model.\n",
"type": "string"
},
"punctuate": {
"x-label": "Punctuate",
"description": "Enable [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false",
"type": "boolean",
"default": true
},
"redact_pii": {
"x-label": "Redact PII",
"description": "Redact PII from the transcribed text using the Redact PII model, can be true or false. Requires `format_text` to be `true`. See [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"type": "boolean",
"default": false
},
"redact_pii_audio": {
"x-label": "Redact PII audio",
"description": "Generate a copy of the original media file with spoken PII \"beeped\" out, can be true or false. Requires `redact_pii` to be `true`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.",
"type": "boolean",
"default": false
},
"redact_pii_audio_options": {
"x-label": "Specify options for PII redacted audio files.",
"description": "Specify options for [PII redacted audio](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) files.",
"type": "object",
"additionalProperties": false,
"properties": {
"return_redacted_no_speech_audio": {
"x-label": "Return redacted no speech audio",
"description": "By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`. Requires `redact_pii_audio` to be `true`.",
"type": "boolean",
"default": false
},
"override_audio_redaction_method": {
"x-label": "Override audio redaction method",
"description": "Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep.",
"type": "string",
"enum": [
"silence"
]
}
}
},
"redact_pii_audio_quality": {
"x-label": "Redact PII audio quality",
"description": "Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.",
"default": "mp3",
"$ref": "#/components/schemas/RedactPiiAudioQuality"
},
"redact_pii_policies": {
"x-label": "Redact PII policies",
"description": "The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"type": "array",
"items": {
"x-label": "PII policy",
"$ref": "#/components/schemas/PiiPolicy"
}
},
"redact_pii_sub": {
"x-label": "Redact PII substitution",
"description": "The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"oneOf": [
{
"$ref": "#/components/schemas/SubstitutionPolicy"
},
{
"type": "null"
}
],
"default": "hash"
},
"redact_pii_return_unredacted": {
"x-label": "Return unredacted transcript",
"description": "When set to `true`, returns the original unredacted transcript alongside the redacted one in the same response. Requires `redact_pii` to be `true`, otherwise a 400 error is returned.\n\nWhen enabled, the response includes the additional fields `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. The existing `text`, `words`, and `utterances` fields remain fully redacted. When disabled (default), the response is unchanged and contains only the redacted transcript. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.\n",
"type": "boolean",
"default": false
},
"redact_static_entities": {
"x-label": "Redact static entities",
"description": "A map of user-defined terms to redact, where each key is a redaction label and each value is a list of exact terms to match (e.g. `{ \"INTERNAL_TOOL\": [\"Bearclaw\", \"Cubclaw\"] }`). Each matching term in the transcript is redacted using the `redact_pii_sub` substitution, on top of standard PII Redaction. Useful for redacting specific, predefined terms (proprietary names, internal codenames) that aren't general PII categories.\n\nThis is a literal find-and-replace (tolerant of casing, surrounding punctuation, and minor spacing/hyphenation), not a model \u2014 it does not generalize beyond the terms you provide. Requires `redact_pii` to be `true`, otherwise a 400 error is returned. When `redact_pii_audio` is enabled, matched terms are also redacted in the audio output. You can provide up to 100 labels, each with up to 200 terms of at most 200 characters; a label may contain only letters, numbers, spaces, underscores, and hyphens (max 80 characters). See [Static Entity Redaction](https://www.assemblyai.com/docs/guardrails/redact-pii-from-transcripts#static-entity-redaction) for more details.\n",
"type": "object",
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"sentiment_analysis": {
"x-label": "Sentiment Analysis",
"description": "Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis), can be true or false. Requires `punctuate` to be `true`.",
"type": "boolean",
"default": false
},
"speaker_labels": {
"x-label": "Speaker labels",
"description": "Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false. Requires `punctuate` to be `true`.",
"type": "boolean",
"default": false
},
"speaker_options": {
"x-label": "Specify options for speaker diarization.",
"description": "Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers). Use this to set a range of possible speakers. Requires `speaker_labels` to be `true`, and cannot be used together with `speakers_expected`. When both bounds are set, `min_speakers_expected` must be less than or equal to `max_speakers_expected`.",
"type": "object",
"additionalProperties": false,
"properties": {
"min_speakers_expected": {
"x-label": "Minimum speakers expected",
"description": "A hard lower limit on the number of speaker labels \u2014 the model won't return fewer speakers than this. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.",
"type": "integer"
},
"max_speakers_expected": {
"x-label": "Maximum speakers expected",
"description": "Setting this parameter too high may hurt model accuracy\nA hard upper limit on the number of speaker labels. If more people speak than this value, the additional speakers are merged into existing labels. Setting it higher than the true number of speakers can cause the model to over-split and return more speakers than are actually present. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.\n",
"type": "integer"
}
}
},
"speakers_expected": {
"x-label": "Speakers expected",
"description": "Tells the speaker label model how many speakers it should attempt to identify. Requires `speaker_labels` to be `true` and must be a positive integer; cannot be used together with `speaker_options`. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details.",
"type": [
"integer",
"null"
],
"default": null
},
"speech_models": {
"x-label": "Speech models",
"description": "Optional. List one or more speech models in priority order. Supported values: `universal-3-5-pro`, `universal-2`. If omitted, defaults to `[\"universal-3-5-pro\", \"universal-2\"]`. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n",
"type": "array",
"items": {
"x-label": "Speech model",
"$ref": "#/components/schemas/SpeechModel"
},
"default": [
"universal-3-5-pro",
"universal-2"
]
},
"speech_threshold": {
"x-label": "Speech threshold",
"description": "Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n",
"type": [
"number",
"null"
],
"format": "float",
"minimum": 0,
"maximum": 1,
"default": 0
},
"speech_understanding": {
"x-label": "Speech Understanding",
"description": "Enable speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n",
"type": "object",
"properties": {
"request": {
"oneOf": [
{
"$ref": "#/components/schemas/TranslationRequestBody"
},
{
"$ref": "#/components/schemas/SpeakerIdentificationRequestBody"
},
{
"$ref": "#/components/schemas/CustomFormattingRequestBody"
},
{
"$ref": "#/components/schemas/SummarizationRequestBody"
},
{
"$ref": "#/components/schemas/ActionItemsRequestBody"
}
]
}
},
"required": [
"request"
]
},
"summarization": {
"x-label": "Enable Summarization",
"description": "Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization), can be true or false. Requires both `punctuate` and `format_text` to be `true`, and cannot be enabled together with `auto_chapters`. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n",
"type": "boolean",
"default": false,
"deprecated": true
},
"summary_model": {
"x-label": "Summary model",
"description": "The model to summarize the transcript. Must be set together with `summary_type`. Compatibility - `catchy` supports `gist` and `headline`; `informative` and `conversational` support `headline`, `paragraph`, `bullets`, and `bullets_verbose`. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.",
"default": "informative",
"deprecated": true,
"$ref": "#/components/schemas/SummaryModel"
},
"summary_type": {
"x-label": "Summary type",
"description": "The type of summary. Must be set together with `summary_model`; see `summary_model` for the supported model and type combinations. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.",
"default": "bullets",
"deprecated": true,
"$ref": "#/components/schemas/SummaryType"
},
"remove_audio_tags": {
"x-label": "Remove audio tags",
"description": "Universal-3.5 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `\"all\"` to remove all inline annotations, or `\"speaker\"` to remove only speaker cues while keeping other annotations. By default, all inline annotations are removed.\n\nNote: This parameter is only supported for the Universal-3.5 Pro model.\n",
"oneOf": [
{
"type": "string",
"enum": [
"all",
"speaker"
]
},
{
"type": "null"
}
],
"default": "all"
},
"temperature": {
"x-label": "Temperature",
"description": "Control the amount of randomness injected into the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter only takes effect on the Universal-3.5 Pro model.\n",
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0
},
"webhook_auth_header_name": {
"x-label": "Webhook auth header name",
"description": "The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests. Must be 1-1000 characters and contain only ASCII letters, numbers, hyphens, and underscores. Requires `webhook_auth_header_value` and `webhook_url` to also be set.",
"type": [
"string",
"null"
],
"default": null
},
"webhook_auth_header_value": {
"x-label": "Webhook auth header value",
"description": "The header value to send back with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests for added security. Must be 1-1000 characters and must not contain carriage returns or newlines. Requires `webhook_auth_header_name` and `webhook_url` to also be set.",
"type": [
"string",
"null"
],
"default": null
},
"webhook_url": {
"x-label": "Webhook URL",
"description": "The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n",
"type": "string",
"format": "url"
},
"custom_topics": {
"x-label": "Enable custom topics",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "boolean",
"default": false,
"deprecated": true
},
"speech_model": {
"x-label": "Speech model",
"description": "This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n",
"oneOf": [
{
"$ref": "#/components/schemas/SpeechModel"
},
{
"type": "null"
}
],
"deprecated": true
},
"topics": {
"x-label": "Custom topics",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "array",
"items": {
"x-label": "Topic",
"type": "string"
},
"deprecated": true
}
},
"example": {
"speech_model": null,
"language_detection": true,
"language_confidence_threshold": 0.7,
"punctuate": true,
"format_text": true,
"multichannel": true,
"webhook_url": "https://your-webhook-url.tld/path",
"webhook_auth_header_name": "webhook-secret",
"webhook_auth_header_value": "webhook-secret-value",
"auto_highlights": true,
"audio_start_from": 10,
"audio_end_at": 280,
"filter_profanity": true,
"redact_pii": true,
"redact_pii_audio": true,
"redact_pii_audio_quality": "mp3",
"redact_pii_policies": [
"us_social_security_number",
"credit_card_number"
],
"redact_pii_sub": "hash",
"speaker_labels": true,
"speakers_expected": 2,
"content_safety": true,
"iab_categories": true,
"custom_spelling": [],
"disfluencies": false,
"sentiment_analysis": true,
"auto_chapters": false,
"entity_detection": true,
"speech_threshold": 0.5,
"summarization": false,
"summary_model": null,
"summary_type": null,
"custom_topics": true,
"topics": [],
"remove_audio_tags": null,
"domain": null,
"speech_understanding": {
"request": {
"translation": {
"target_languages": [
"es",
"de"
],
"formal": true,
"match_original_utterance": true
}
}
}
}
},
"TranscriptParams": {
"x-label": "Transcript parameters",
"description": "The parameters for creating a transcript",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"allOf": [
{
"type": "object",
"required": [
"audio_url"
],
"properties": {
"audio_url": {
"x-label": "Audio URL",
"description": "The URL of the audio or video file to transcribe.",
"type": "string",
"format": "url"
}
},
"additionalProperties": false
},
{
"$ref": "#/components/schemas/TranscriptOptionalParams"
}
],
"example": {
"speech_model": null,
"language_detection": true,
"language_confidence_threshold": 0.7,
"audio_url": "https://assembly.ai/wildfires.mp3",
"punctuate": true,
"format_text": true,
"multichannel": true,
"webhook_url": "https://your-webhook-url/path",
"webhook_auth_header_name": "webhook-secret",
"webhook_auth_header_value": "webhook-secret-value",
"auto_highlights": true,
"audio_start_from": 10,
"audio_end_at": 280,
"filter_profanity": true,
"redact_pii": true,
"redact_pii_audio": true,
"redact_pii_audio_quality": "mp3",
"redact_pii_policies": [
"us_social_security_number",
"credit_card_number"
],
"redact_pii_sub": "hash",
"speaker_labels": true,
"speakers_expected": 2,
"content_safety": true,
"iab_categories": true,
"custom_spelling": [],
"disfluencies": false,
"sentiment_analysis": true,
"auto_chapters": false,
"entity_detection": true,
"speech_threshold": 0.5,
"summarization": false,
"summary_model": null,
"summary_type": null,
"custom_topics": true,
"topics": [],
"remove_audio_tags": null,
"domain": null,
"speech_understanding": {
"request": {
"translation": {
"target_languages": [
"es",
"de"
],
"formal": true,
"match_original_utterance": true
}
}
}
}
},
"SummaryModel": {
"type": "string",
"x-label": "Summary model",
"description": "The model to summarize the transcript",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"informative",
"conversational",
"catchy"
],
"x-aai-enum": {
"informative": {
"label": "Informative"
},
"conversational": {
"label": "Conversational"
},
"catchy": {
"label": "Catchy"
}
}
},
"SummaryType": {
"type": "string",
"x-label": "Summary type",
"description": "The type of summary",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"bullets",
"bullets_verbose",
"gist",
"headline",
"paragraph"
],
"x-aai-enum": {
"bullets": {
"label": "Bullets"
},
"bullets_verbose": {
"label": "Bullets verbose"
},
"gist": {
"label": "Gist"
},
"headline": {
"label": "Headline"
},
"paragraph": {
"label": "Paragraph"
}
}
},
"TranscriptCustomSpelling": {
"x-label": "Custom spelling",
"description": "Object containing words or phrases to replace, and the word or phrase to replace with",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"properties": {
"from": {
"x-label": "From",
"description": "Words or phrases to replace",
"type": "array",
"items": {
"x-label": "Word or phrase",
"description": "Word or phrase to replace",
"type": "string"
}
},
"to": {
"x-label": "To",
"description": "Word to replace with",
"type": "string"
}
},
"required": [
"from",
"to"
],
"example": {
"from": [
"dicarlo"
],
"to": "Decarlo"
}
},
"TranscriptUtterance": {
"type": "object",
"x-label": "Utterance",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"properties": {
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript of this utterance",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, of the utterance in the audio file",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The ending time, in milliseconds, of the utterance in the audio file",
"type": "integer"
},
"text": {
"x-label": "Text",
"description": "The text for this utterance",
"type": "string"
},
"words": {
"x-label": "Words",
"description": "The words in the utterance.",
"type": "array",
"items": {
"x-label": "Word",
"$ref": "#/components/schemas/TranscriptWord"
}
},
"channel": {
"x-label": "Channel",
"description": "The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.",
"type": [
"string",
"null"
]
},
"speaker": {
"x-label": "Speaker",
"description": "The speaker of this utterance, where each speaker is assigned a sequential capital letter - e.g. \"A\" for Speaker A, \"B\" for Speaker B, etc.",
"type": "string"
},
"translated_texts": {
"x-label": "Translated texts",
"description": "Translations keyed by language code (e.g., `{\"es\": \"Texto traducido\", \"de\": \"\u00dcbersetzter Text\"}`). Only present when `match_original_utterance` is enabled with translation.",
"type": "object",
"additionalProperties": {
"type": "string"
}
}
},
"required": [
"confidence",
"start",
"end",
"text",
"words",
"speaker"
],
"example": {
"confidence": 0.9359033333333334,
"end": 26950,
"speaker": "A",
"start": 250,
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor.",
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.97503,
"speaker": "A"
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 0.99999,
"speaker": "A"
},
{
"text": "hundreds",
"start": 1076,
"end": 1418,
"confidence": 0.99843,
"speaker": "A"
},
{
"text": "of",
"start": 1434,
"end": 1614,
"confidence": 0.85,
"speaker": "A"
},
{
"text": "wildfires",
"start": 1652,
"end": 2346,
"confidence": 0.89657,
"speaker": "A"
},
{
"text": "in",
"start": 2378,
"end": 2526,
"confidence": 0.99994,
"speaker": "A"
},
{
"text": "Canada",
"start": 2548,
"end": 3130,
"confidence": 0.93864,
"speaker": "A"
},
{
"text": "is",
"start": 3210,
"end": 3454,
"confidence": 0.999,
"speaker": "A"
},
{
"text": "triggering",
"start": 3492,
"end": 3946,
"confidence": 0.75366,
"speaker": "A"
},
{
"text": "air",
"start": 3978,
"end": 4174,
"confidence": 1,
"speaker": "A"
},
{
"text": "quality",
"start": 4212,
"end": 4558,
"confidence": 0.87745,
"speaker": "A"
},
{
"text": "alerts",
"start": 4644,
"end": 5114,
"confidence": 0.94739,
"speaker": "A"
},
{
"text": "throughout",
"start": 5162,
"end": 5466,
"confidence": 0.99726,
"speaker": "A"
},
{
"text": "the",
"start": 5498,
"end": 5694,
"confidence": 0.79,
"speaker": "A"
},
{
"text": "US.",
"start": 5732,
"end": 6382,
"confidence": 0.88,
"speaker": "A"
}
]
}
},
"SubstitutionPolicy": {
"x-label": "Redact PII substitution",
"type": "string",
"x-fern-sdk-group-name": "transcripts",
"description": "The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"enum": [
"entity_name",
"hash"
],
"x-aai-enum": {
"entity_name": {
"label": "Entity name"
},
"hash": {
"label": "Hash"
}
}
},
"RedactPiiAudioQuality": {
"x-label": "Redact PII audio quality",
"type": "string",
"description": "Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"mp3",
"wav"
],
"x-fern-enum": {
"mp3": {
"description": "MP3 audio format is lower quality and lower size than WAV.",
"casing": {
"camel": "mp3",
"snake": "mp3",
"pascal": "Mp3",
"screamingSnake": "MP3"
}
},
"wav": {
"description": "WAV audio format is the highest quality (no compression) and larger size than MP3."
}
},
"x-aai-enum": {
"mp3": {
"label": "MP3"
},
"wav": {
"label": "WAV"
}
},
"example": "mp3"
},
"PiiPolicy": {
"x-label": "PII policy",
"description": "The type of PII to redact",
"x-fern-sdk-group-name": "transcripts",
"type": "string",
"enum": [
"account_number",
"banking_information",
"blood_type",
"credit_card_cvv",
"credit_card_expiration",
"credit_card_number",
"date",
"date_interval",
"date_of_birth",
"drivers_license",
"drug",
"duration",
"email_address",
"event",
"filename",
"gender",
"gender_sexuality",
"healthcare_number",
"injury",
"ip_address",
"language",
"location",
"location_address",
"location_address_street",
"location_city",
"location_coordinate",
"location_country",
"location_state",
"location_zip",
"marital_status",
"medical_condition",
"medical_process",
"money_amount",
"nationality",
"number_sequence",
"occupation",
"organization",
"organization_medical_facility",
"passport_number",
"password",
"person_age",
"person_name",
"phone_number",
"physical_attribute",
"political_affiliation",
"religion",
"sexuality",
"statistics",
"time",
"url",
"us_social_security_number",
"username",
"vehicle_id",
"zodiac_sign"
],
"x-fern-enum": {
"account_number": {
"description": "Customer account or membership identification number (e.g., Policy No. 10042992, Member ID: HZ-5235-001)"
},
"banking_information": {
"description": "Banking information, including account and routing numbers"
},
"blood_type": {
"description": "Blood type (e.g., O-, AB positive)"
},
"credit_card_cvv": {
"description": "Credit card verification code (e.g., CVV: 080)"
},
"credit_card_expiration": {
"description": "Expiration date of a credit card"
},
"credit_card_number": {
"description": "Credit card number"
},
"date": {
"description": "Specific calendar date (e.g., December 18)"
},
"date_interval": {
"description": "Broader time periods, including date ranges, months, seasons, years, and decades (e.g., 2020-2021, 5-9 May, January 1984)"
},
"date_of_birth": {
"description": "Date of birth (e.g., Date of Birth: March 7,1961)"
},
"drivers_license": {
"description": "Driver's license number. (e.g., DL# 356933-540)"
},
"drug": {
"description": "Medications, vitamins, or supplements (e.g., Advil, Acetaminophen, Panadol)"
},
"duration": {
"description": "Measurements of time expressed as a numerical value plus a unit (e.g., 8 months, 2 years)"
},
"email_address": {
"description": "Email address (e.g., support@assemblyai.com)"
},
"event": {
"description": "Name of an event or holiday (e.g., Olympics, Yom Kippur)"
},
"filename": {
"description": "Names of computer files, including the extension or filepath (e.g., Taxes/2012/brad-tax-returns.pdf)"
},
"gender": {
"description": "Terms indicating gender identity (e.g., female, male, non-binary)"
},
"gender_sexuality": {
"description": "Terms indicating gender identity or sexual orientation, including slang terms (e.g., female, bisexual, trans)"
},
"healthcare_number": {
"description": "Healthcare numbers and health plan beneficiary numbers (e.g., Policy No.: 5584-486-674-YM)"
},
"injury": {
"description": "Bodily injury (e.g., I broke my arm, I have a sprained wrist)"
},
"ip_address": {
"description": "Internet IP address, including IPv4 and IPv6 formats (e.g., 192.168.0.1)"
},
"language": {
"description": "Name of a natural language (e.g., Spanish, French)"
},
"location": {
"description": "Any Location reference including mailing address, postal code, city, state, province, country, or coordinates. (e.g., Lake Victoria, 145 Windsor St., 90210)"
},
"location_address": {
"description": "A complete mailing address (e.g., 145 Windsor St., Toronto, ON M5A 2P5)"
},
"location_address_street": {
"description": "Street-level component of an address (e.g., 145 Windsor St.)"
},
"location_city": {
"description": "City name (e.g., Toronto, San Francisco)"
},
"location_coordinate": {
"description": "Geographic coordinates (e.g., 40.7128\u00b0 N, 74.0060\u00b0 W)"
},
"location_country": {
"description": "Country name (e.g., Canada, United States)"
},
"location_state": {
"description": "State, province, or region name (e.g., Ontario, California)"
},
"location_zip": {
"description": "Postal or ZIP code (e.g., M5A 2P5, 90210)"
},
"marital_status": {
"description": "Terms indicating marital status (e.g., Single, common-law, ex-wife, married)"
},
"medical_condition": {
"description": "Name of a medical condition, disease, syndrome, deficit, or disorder (e.g., chronic fatigue syndrome, arrhythmia, depression)"
},
"medical_process": {
"description": "Medical process, including treatments, procedures, and tests (e.g., heart surgery, CT scan)"
},
"money_amount": {
"description": "Name and/or amount of currency (e.g., 15 pesos, $94.50)"
},
"nationality": {
"description": "Terms indicating nationality, ethnicity, or race (e.g., American, Asian, Caucasian)"
},
"number_sequence": {
"description": "Numerical PII (including alphanumeric strings) that doesn't fall under other categories"
},
"occupation": {
"description": "Job title or profession (e.g., professor, actors, engineer, CPA)"
},
"organization": {
"description": "Name of an organization (e.g., CNN, McDonalds, University of Alaska, Northwest General Hospital)"
},
"organization_medical_facility": {
"description": "Name of a medical facility (e.g., Mayo Clinic, Northwest General Hospital)"
},
"passport_number": {
"description": "Passport numbers, issued by any country (e.g., PA4568332, NU3C6L86S12)"
},
"password": {
"description": "Account passwords, PINs, access keys, or verification answers (e.g., 27%alfalfa, temp1234, My mother's maiden name is Smith)"
},
"person_age": {
"description": "Number associated with an age (e.g., 27, 75)"
},
"person_name": {
"description": "Name of a person (e.g., Bob, Doug Jones, Dr. Kay Martinez, MD)"
},
"phone_number": {
"description": "Telephone or fax number"
},
"physical_attribute": {
"description": "Distinctive bodily attributes, including race (e.g., I'm 190cm tall, He belongs to the Black students' association)"
},
"political_affiliation": {
"description": "Terms referring to a political party, movement, or ideology (e.g., Republican, Liberal)"
},
"religion": {
"description": "Terms indicating religious affiliation (e.g., Hindu, Catholic)"
},
"sexuality": {
"description": "Terms indicating sexual orientation (e.g., heterosexual, bisexual, gay)"
},
"statistics": {
"description": "Medical statistics (e.g., 18%, 18 percent)"
},
"time": {
"description": "Expressions indicating clock times (e.g., 19:37:28, 10pm EST)"
},
"url": {
"description": "Internet addresses (e.g., https://www.assemblyai.com/)"
},
"us_social_security_number": {
"description": "Social Security Number or equivalent"
},
"username": {
"description": "Usernames, login names, or handles (e.g., @AssemblyAI)"
},
"vehicle_id": {
"description": "Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers (e.g., 5FNRL38918B111818, BIF7547)"
},
"zodiac_sign": {
"description": "Names of Zodiac signs (e.g., Aries, Taurus)"
}
},
"x-aai-enum": {
"account_number": {
"label": "Account number"
},
"banking_information": {
"label": "Banking information"
},
"blood_type": {
"label": "Blood type"
},
"credit_card_cvv": {
"label": "Credit card CVV"
},
"credit_card_expiration": {
"label": "Credit card expiration"
},
"credit_card_number": {
"label": "Credit card number"
},
"date": {
"label": "Date"
},
"date_interval": {
"label": "Date interval"
},
"date_of_birth": {
"label": "Date of birth"
},
"drivers_license": {
"label": "Driver's license"
},
"drug": {
"label": "Drug"
},
"duration": {
"label": "Duration"
},
"email_address": {
"label": "Email address"
},
"event": {
"label": "Event"
},
"filename": {
"label": "Filename"
},
"gender": {
"label": "Gender"
},
"gender_sexuality": {
"label": "Gender sexuality"
},
"healthcare_number": {
"label": "Healthcare number"
},
"injury": {
"label": "Injury"
},
"ip_address": {
"label": "IP address"
},
"language": {
"label": "Language"
},
"location": {
"label": "Location"
},
"location_address": {
"label": "Location address"
},
"location_address_street": {
"label": "Location address street"
},
"location_city": {
"label": "Location city"
},
"location_coordinate": {
"label": "Location coordinate"
},
"location_country": {
"label": "Location country"
},
"location_state": {
"label": "Location state"
},
"location_zip": {
"label": "Location ZIP"
},
"marital_status": {
"label": "Marital status"
},
"medical_condition": {
"label": "Medical condition"
},
"medical_process": {
"label": "Medical process"
},
"money_amount": {
"label": "Money amount"
},
"nationality": {
"label": "Nationality"
},
"number_sequence": {
"label": "Number sequence"
},
"occupation": {
"label": "Occupation"
},
"organization": {
"label": "Organization"
},
"organization_medical_facility": {
"label": "Organization medical facility"
},
"passport_number": {
"label": "Passport number"
},
"password": {
"label": "Password"
},
"person_age": {
"label": "Person age"
},
"person_name": {
"label": "Person name"
},
"phone_number": {
"label": "Phone number"
},
"physical_attribute": {
"label": "Physical attribute"
},
"political_affiliation": {
"label": "Political affiliation"
},
"religion": {
"label": "Religion"
},
"sexuality": {
"label": "Sexuality"
},
"statistics": {
"label": "Statistics"
},
"time": {
"label": "Time"
},
"url": {
"label": "URL"
},
"us_social_security_number": {
"label": "US Social Security Number"
},
"username": {
"label": "Username"
},
"vehicle_id": {
"label": "Vehicle ID"
},
"zodiac_sign": {
"label": "Zodiac sign"
}
}
},
"SpeechModel": {
"x-label": "Speech model",
"type": "string",
"description": "The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models.",
"enum": [
"universal-3-5-pro",
"universal-2"
],
"x-fern-sdk-group-name": "transcripts"
},
"TranscriptLanguageCode": {
"x-label": "Language code",
"type": "string",
"description": "The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\n",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"en",
"en_au",
"en_uk",
"en_us",
"es",
"fr",
"de",
"it",
"pt",
"nl",
"af",
"sq",
"am",
"ar",
"hy",
"as",
"az",
"ba",
"eu",
"be",
"bn",
"bs",
"br",
"bg",
"my",
"ca",
"zh",
"hr",
"cs",
"da",
"et",
"fo",
"fi",
"gl",
"ka",
"el",
"gu",
"ht",
"ha",
"haw",
"he",
"hi",
"hu",
"is",
"id",
"ja",
"jw",
"kn",
"kk",
"km",
"ko",
"lo",
"la",
"lv",
"ln",
"lt",
"lb",
"mk",
"mg",
"ms",
"ml",
"mt",
"mi",
"mr",
"mn",
"ne",
"no",
"nn",
"oc",
"pa",
"ps",
"fa",
"pl",
"ro",
"ru",
"sa",
"sr",
"sn",
"sd",
"si",
"sk",
"sl",
"so",
"su",
"sw",
"sv",
"tl",
"tg",
"ta",
"tt",
"te",
"th",
"bo",
"tr",
"tk",
"uk",
"ur",
"uz",
"vi",
"cy",
"yi",
"yo"
],
"x-aai-enum": {
"en": {
"label": "English (global)"
},
"en_au": {
"label": "English (Australian)"
},
"en_uk": {
"label": "English (British)"
},
"en_us": {
"label": "English (US)"
},
"es": {
"label": "Spanish"
},
"fr": {
"label": "French"
},
"de": {
"label": "German"
},
"it": {
"label": "Italian"
},
"pt": {
"label": "Portuguese"
},
"nl": {
"label": "Dutch"
},
"af": {
"label": "Afrikaans"
},
"sq": {
"label": "Albanian"
},
"am": {
"label": "Amharic"
},
"ar": {
"label": "Arabic"
},
"hy": {
"label": "Armenian"
},
"as": {
"label": "Assamese"
},
"az": {
"label": "Azerbaijani"
},
"ba": {
"label": "Bashkir"
},
"eu": {
"label": "Basque"
},
"be": {
"label": "Belarusian"
},
"bn": {
"label": "Bengali"
},
"bs": {
"label": "Bosnian"
},
"br": {
"label": "Breton"
},
"bg": {
"label": "Bulgarian"
},
"my": {
"label": "Burmese"
},
"ca": {
"label": "Catalan"
},
"zh": {
"label": "Chinese"
},
"hr": {
"label": "Croatian"
},
"cs": {
"label": "Czech"
},
"da": {
"label": "Danish"
},
"et": {
"label": "Estonian"
},
"fo": {
"label": "Faroese"
},
"fi": {
"label": "Finnish"
},
"gl": {
"label": "Galician"
},
"ka": {
"label": "Georgian"
},
"el": {
"label": "Greek"
},
"gu": {
"label": "Gujarati"
},
"ht": {
"label": "Haitian"
},
"ha": {
"label": "Hausa"
},
"haw": {
"label": "Hawaiian"
},
"he": {
"label": "Hebrew"
},
"hi": {
"label": "Hindi"
},
"hu": {
"label": "Hungarian"
},
"is": {
"label": "Icelandic"
},
"id": {
"label": "Indonesian"
},
"ja": {
"label": "Japanese"
},
"jw": {
"label": "Javanese"
},
"kn": {
"label": "Kannada"
},
"kk": {
"label": "Kazakh"
},
"km": {
"label": "Khmer"
},
"ko": {
"label": "Korean"
},
"lo": {
"label": "Lao"
},
"la": {
"label": "Latin"
},
"lv": {
"label": "Latvian"
},
"ln": {
"label": "Lingala"
},
"lt": {
"label": "Lithuanian"
},
"lb": {
"label": "Luxembourgish"
},
"mk": {
"label": "Macedonian"
},
"mg": {
"label": "Malagasy"
},
"ms": {
"label": "Malay"
},
"ml": {
"label": "Malayalam"
},
"mt": {
"label": "Maltese"
},
"mi": {
"label": "Maori"
},
"mr": {
"label": "Marathi"
},
"mn": {
"label": "Mongolian"
},
"ne": {
"label": "Nepali"
},
"no": {
"label": "Norwegian"
},
"nn": {
"label": "Norwegian Nynorsk"
},
"oc": {
"label": "Occitan"
},
"pa": {
"label": "Panjabi"
},
"ps": {
"label": "Pashto"
},
"fa": {
"label": "Persian"
},
"pl": {
"label": "Polish"
},
"ro": {
"label": "Romanian"
},
"ru": {
"label": "Russian"
},
"sa": {
"label": "Sanskrit"
},
"sr": {
"label": "Serbian"
},
"sn": {
"label": "Shona"
},
"sd": {
"label": "Sindhi"
},
"si": {
"label": "Sinhala"
},
"sk": {
"label": "Slovak"
},
"sl": {
"label": "Slovenian"
},
"so": {
"label": "Somali"
},
"su": {
"label": "Sundanese"
},
"sw": {
"label": "Swahili"
},
"sv": {
"label": "Swedish"
},
"tl": {
"label": "Tagalog"
},
"tg": {
"label": "Tajik"
},
"ta": {
"label": "Tamil"
},
"tt": {
"label": "Tatar"
},
"te": {
"label": "Telugu"
},
"th": {
"label": "Thai"
},
"bo": {
"label": "Tibetan"
},
"tr": {
"label": "Turkish"
},
"tk": {
"label": "Turkmen"
},
"uk": {
"label": "Ukrainian"
},
"ur": {
"label": "Urdu"
},
"uz": {
"label": "Uzbek"
},
"vi": {
"label": "Vietnamese"
},
"cy": {
"label": "Welsh"
},
"yi": {
"label": "Yiddish"
},
"yo": {
"label": "Yoruba"
}
}
},
"TranscriptStatus": {
"x-label": "Status",
"type": "string",
"description": "The status of your transcript. Possible values are queued, processing, completed, or error.",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"queued",
"processing",
"completed",
"error"
],
"x-fern-enum": {
"queued": {
"description": "The audio file is in the queue to be processed by the API."
},
"processing": {
"description": "The audio file is being processed by the API."
},
"completed": {
"description": "The transcript job has been completed successfully."
},
"error": {
"description": "An error occurred while processing the audio file."
}
},
"x-aai-enum": {
"queued": {
"label": "Queued"
},
"processing": {
"label": "Processing"
},
"completed": {
"label": "Completed"
},
"error": {
"label": "Error"
}
}
},
"TranscriptReadyStatus": {
"x-label": "Status",
"type": "string",
"description": "The status of the transcript. Either completed or error.",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"completed",
"error"
],
"x-fern-enum": {
"completed": {
"description": "The transcript job has been completed successfully."
},
"error": {
"description": "An error occurred while processing the audio file."
}
},
"x-aai-enum": {
"completed": {
"label": "Completed"
},
"error": {
"label": "Error"
}
}
},
"Transcript": {
"x-label": "Transcript",
"description": "A transcript object",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"properties": {
"audio_channels": {
"x-label": "Audio channels",
"description": "The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled.",
"type": "integer"
},
"audio_duration": {
"x-label": "Audio duration",
"description": "The duration of this transcript object's media file, in seconds",
"type": [
"integer",
"null"
]
},
"audio_end_at": {
"x-label": "Audio end at",
"description": "The point in time, in milliseconds, in the file at which the transcription was terminated. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.",
"type": [
"integer",
"null"
]
},
"audio_start_from": {
"x-label": "Audio start from",
"description": "The point in time, in milliseconds, in the file at which the transcription was started. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.",
"type": [
"integer",
"null"
]
},
"audio_url": {
"x-label": "Audio URL",
"description": "The URL of the media that was transcribed",
"type": "string",
"format": "url"
},
"auto_chapters": {
"x-label": "Auto Chapters enabled",
"description": "Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n",
"type": [
"boolean",
"null"
],
"deprecated": true
},
"auto_highlights": {
"x-label": "Key Phrases",
"description": "Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) is enabled, either true or false",
"type": "boolean"
},
"auto_highlights_result": {
"x-label": "Key Phrases result",
"description": "An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n",
"oneOf": [
{
"$ref": "#/components/schemas/AutoHighlightsResult"
},
{
"type": "null"
}
]
},
"chapters": {
"x-label": "Chapters",
"description": "An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for more information.",
"type": [
"array",
"null"
],
"items": {
"x-label": "Chapter",
"$ref": "#/components/schemas/Chapter"
}
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)",
"type": [
"number",
"null"
],
"format": "double",
"minimum": 0,
"maximum": 1
},
"content_safety": {
"x-label": "Content Moderation",
"description": "Whether [Content Moderation](https://www.assemblyai.com/docs/content-moderation) is enabled, can be true or false",
"type": [
"boolean",
"null"
]
},
"content_safety_labels": {
"x-label": "Content Moderation labels",
"description": "An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n",
"oneOf": [
{
"$ref": "#/components/schemas/ContentSafetyLabelsResult"
},
{
"type": "null"
}
]
},
"custom_spelling": {
"x-label": "Custom spellings",
"description": "Customize how words are spelled and formatted using to and from values. Each `to` value must be a single word, and each `from` phrase can contain at most 5 words. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details.",
"type": [
"array",
"null"
],
"items": {
"x-label": "Custom spelling",
"$ref": "#/components/schemas/TranscriptCustomSpelling"
}
},
"disfluencies": {
"x-label": "Disfluencies",
"description": "Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like \"umm\", in your media file; can be true or false. Supported on Universal-3.5 Pro and Universal-2.",
"type": [
"boolean",
"null"
]
},
"domain": {
"x-label": "Domain",
"description": "The domain-specific model applied to the transcript. When set to `\"medical-v1\"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n",
"type": [
"string",
"null"
]
},
"entities": {
"x-label": "Entities",
"description": "An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) for more information.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Entity",
"$ref": "#/components/schemas/Entity"
}
},
"entity_detection": {
"x-label": "Entity Detection",
"description": "Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) is enabled, can be true or false",
"type": [
"boolean",
"null"
]
},
"error": {
"x-label": "Error",
"description": "Error message of why the transcript failed",
"type": "string"
},
"filter_profanity": {
"x-label": "Filter profanity",
"description": "Whether [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) is enabled, either true or false",
"type": [
"boolean",
"null"
]
},
"format_text": {
"x-label": "Format text",
"description": "Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false",
"type": [
"boolean",
"null"
]
},
"iab_categories": {
"x-label": "Topic Detection",
"description": "Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) is enabled, can be true or false",
"type": [
"boolean",
"null"
]
},
"iab_categories_result": {
"x-label": "Topic Detection result",
"description": "The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n",
"oneOf": [
{
"$ref": "#/components/schemas/TopicDetectionModelResult"
},
{
"type": "null"
}
]
},
"id": {
"x-label": "ID",
"description": "The unique identifier of your transcript",
"type": "string",
"format": "uuid"
},
"keyterms_prompt": {
"x-label": "Keyterms prompt",
"description": "Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3.5 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro/prompting#keyterms-prompting) for more details.\n",
"type": "array",
"items": {
"x-label": "Keyterm",
"type": "string"
}
},
"language_code": {
"x-label": "Language code",
"description": "The language of your audio file.\nPossible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\n",
"anyOf": [
{
"$ref": "#/components/schemas/TranscriptLanguageCode"
},
{
"type": "string"
}
],
"x-ts-type": "LiteralUnion",
"x-go-type": "TranscriptLanguageCode"
},
"language_codes": {
"description": "The language codes of your audio file. Used for [Code switching](/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Language code",
"$ref": "#/components/schemas/TranscriptLanguageCode"
}
},
"language_confidence": {
"x-label": "Language confidence",
"description": "The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.",
"type": [
"number",
"null"
],
"format": "double",
"minimum": 0,
"maximum": 1
},
"language_confidence_threshold": {
"x-label": "Language confidence threshold",
"description": "The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nSee [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": [
"number",
"null"
],
"format": "float",
"minimum": 0,
"maximum": 1
},
"language_detection": {
"x-label": "Language detection",
"description": "Whether [Automatic language detection](/pre-recorded-audio/automatic-language-detection) is enabled, either true or false",
"type": [
"boolean",
"null"
]
},
"language_detection_options": {
"x-label": "Specify options for Automatic Language Detection.",
"description": "Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection).",
"type": "object",
"additionalProperties": false,
"properties": {
"expected_languages": {
"x-label": "Expected languages",
"description": "List of languages expected in the audio file. Defaults to `[\"all\"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.",
"type": "array",
"items": {
"x-label": "language",
"type": "string"
}
},
"fallback_language": {
"x-label": "Fallback language",
"description": "If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `[\"auto\"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "string",
"default": "auto"
},
"code_switching": {
"x-label": "Code switching",
"description": "Whether [code switching](/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n",
"type": "boolean",
"default": false
},
"code_switching_confidence_threshold": {
"x-label": "Code switching confidence threshold",
"description": "The confidence threshold for [code switching](/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n",
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.3
},
"localization": {
"x-label": "Localization",
"description": "Render the transcript in a regional variant of the detected language. Supported values are `en_au` (Australian English) and `en_uk` (British English) — only English is supported today, and you can specify at most one locale per base language. Base or default-region codes such as `en` and `en_us` are not localization variants and return a `400`.\n\nWhen the detected language matches the requested locale's base language, the transcript uses that locale's spelling and `language_code` returns the region-aware code (for example `en_au`) instead of the base `en`. Otherwise, when the detected language isn't available as a locale, the option is ignored. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "array",
"items": {
"x-label": "locale",
"type": "string"
}
},
"on_no_speech_detected": {
"x-label": "On no speech detected",
"description": "Controls what happens when no speech is detected in the audio. With `error` (the default), the transcript fails and the reason is returned in `error`. With `fallback`, the transcript completes with an empty `text`, `language_code` is set to the `fallback_language`, and an explanatory warning is returned in `metadata.warnings`.\n\n`fallback` requires `fallback_language` to be set to a specific language code; `auto` returns a `400`. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "string",
"enum": [
"error",
"fallback"
],
"default": "error"
}
}
},
"metadata": {
"x-label": "Metadata",
"description": "Additional information about the transcript, including any warnings raised while processing the request.",
"type": [
"object",
"null"
],
"properties": {
"warnings": {
"x-label": "Warnings",
"description": "Warnings raised while processing the request, for example when [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) was skipped because the audio contained no speech.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Warning",
"type": "object",
"properties": {
"message": {
"x-label": "Message",
"description": "A human-readable description of the warning.",
"type": "string"
}
}
}
}
}
},
"multichannel": {
"x-label": "Multichannel",
"description": "Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false",
"type": [
"boolean",
"null"
]
},
"prompt": {
"x-label": "Prompt",
"description": "Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3.5 Pro model.\n",
"type": "string"
},
"punctuate": {
"x-label": "Punctuate",
"description": "Whether [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false",
"type": [
"boolean",
"null"
]
},
"redact_pii": {
"x-label": "Redact PII",
"description": "Whether [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) is enabled, either true or false",
"type": "boolean"
},
"redact_pii_audio": {
"x-label": "Redact PII audio",
"description": "Whether a redacted version of the audio file was generated,\neither true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n",
"type": [
"boolean",
"null"
]
},
"redact_pii_audio_options": {
"x-label": "Redact PII audio options",
"description": "The options for PII-redacted audio, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n",
"type": "object",
"additionalProperties": false,
"properties": {
"return_redacted_no_speech_audio": {
"x-label": "Return redacted no speech audio",
"description": "By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`. Requires `redact_pii_audio` to be `true`.",
"type": "boolean",
"default": false
},
"override_audio_redaction_method": {
"x-label": "Override audio redaction method",
"description": "Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep.",
"type": "string",
"enum": [
"silence"
]
}
}
},
"redact_pii_audio_quality": {
"x-label": "Redact PII audio quality",
"description": "The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information.\n",
"oneOf": [
{
"$ref": "#/components/schemas/RedactPiiAudioQuality"
},
{
"type": "null"
}
]
},
"redact_pii_policies": {
"x-label": "Redact PII policies",
"description": "The list of PII Redaction policies that were enabled, if PII Redaction is enabled.\nSee [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "PII policy",
"$ref": "#/components/schemas/PiiPolicy"
}
},
"redact_pii_sub": {
"x-label": "Redact PII substitution",
"description": "The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"$ref": "#/components/schemas/SubstitutionPolicy"
},
"redact_pii_return_unredacted": {
"x-label": "Return unredacted transcript",
"description": "Whether the original unredacted transcript was also returned alongside the redacted one. When `true`, the response includes `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n",
"type": [
"boolean",
"null"
]
},
"sentiment_analysis": {
"x-label": "Sentiment Analysis",
"description": "Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) is enabled, can be true or false",
"type": [
"boolean",
"null"
]
},
"sentiment_analysis_results": {
"x-label": "Sentiment Analysis results",
"description": "An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) for more information.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Sentiment Analysis result",
"$ref": "#/components/schemas/SentimentAnalysisResult"
}
},
"speaker_labels": {
"x-label": "Speaker labels",
"description": "Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false",
"type": [
"boolean",
"null"
]
},
"speakers_expected": {
"x-label": "Speakers expected",
"description": "Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details.",
"type": [
"integer",
"null"
]
},
"speech_model_used": {
"x-label": "Speech model used",
"description": "The speech model that was actually used for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models.",
"type": "string",
"$ref": "#/components/schemas/SpeechModel"
},
"speech_models": {
"x-label": "Speech models",
"description": "List of speech models that were used (in priority order) to transcribe the audio. If not specified in the request, this defaults to `[\"universal-3-5-pro\", \"universal-2\"]`. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Speech model",
"$ref": "#/components/schemas/SpeechModel"
}
},
"speech_threshold": {
"x-label": "Speech threshold",
"description": "Defaults to null. Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n",
"type": [
"number",
"null"
],
"minimum": 0,
"maximum": 1,
"format": "float"
},
"speech_understanding": {
"x-label": "Speech Understanding",
"description": "Speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n",
"type": "object",
"properties": {
"request": {
"oneOf": [
{
"$ref": "#/components/schemas/TranslationRequestBody"
},
{
"$ref": "#/components/schemas/SpeakerIdentificationRequestBody"
},
{
"$ref": "#/components/schemas/CustomFormattingRequestBody"
},
{
"$ref": "#/components/schemas/SummarizationRequestBody"
},
{
"$ref": "#/components/schemas/ActionItemsRequestBody"
}
]
},
"response": {
"oneOf": [
{
"$ref": "#/components/schemas/TranslationResponse"
},
{
"$ref": "#/components/schemas/SpeakerIdentificationResponse"
},
{
"$ref": "#/components/schemas/CustomFormattingResponse"
},
{
"$ref": "#/components/schemas/SummarizationResponse"
},
{
"$ref": "#/components/schemas/ActionItemsResponse"
}
]
}
}
},
"status": {
"x-label": "Status",
"description": "The status of your transcript. Possible values are queued, processing, completed, or error.",
"$ref": "#/components/schemas/TranscriptStatus"
},
"summarization": {
"x-label": "Summarization enabled",
"description": "Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n",
"type": "boolean",
"deprecated": true
},
"summary": {
"x-label": "Summary",
"description": "The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.",
"type": [
"string",
"null"
],
"deprecated": true
},
"summary_model": {
"x-label": "Summary model",
"description": "The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n",
"type": [
"string",
"null"
],
"deprecated": true
},
"summary_type": {
"x-label": "Summary type",
"description": "The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.",
"type": [
"string",
"null"
],
"deprecated": true
},
"remove_audio_tags": {
"x-label": "Remove audio tags",
"description": "Universal-3.5 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `\"all\"` to remove all inline annotations, or `\"speaker\"` to remove only speaker cues while keeping other annotations. By default, all inline annotations are removed.\n\nNote: This parameter is only supported for the Universal-3.5 Pro model.\n",
"oneOf": [
{
"type": "string",
"enum": [
"all",
"speaker"
]
},
{
"type": "null"
}
]
},
"temperature": {
"x-label": "Temperature",
"description": "The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter only takes effect on the Universal-3.5 Pro model.\n",
"type": [
"number",
"null"
],
"minimum": 0,
"maximum": 1
},
"text": {
"x-label": "Text",
"description": "The textual transcript of your media file",
"type": [
"string",
"null"
]
},
"unredacted_text": {
"x-label": "Unredacted text",
"description": "The original textual transcript of your media file before PII redaction was applied. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `text` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n",
"type": [
"string",
"null"
]
},
"throttled": {
"x-label": "Throttled",
"description": "True while a request is throttled and false when a request is no longer throttled",
"type": [
"boolean",
"null"
]
},
"utterances": {
"x-label": "Utterances",
"description": "When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Utterance",
"$ref": "#/components/schemas/TranscriptUtterance"
}
},
"unredacted_utterances": {
"x-label": "Unredacted utterances",
"description": "The original turn-by-turn utterance objects before PII redaction was applied. Same shape as `utterances`. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `utterances` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Utterance",
"$ref": "#/components/schemas/TranscriptUtterance"
}
},
"webhook_auth": {
"x-label": "Webhook auth enabled",
"description": "Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided",
"type": "boolean"
},
"webhook_auth_header_name": {
"x-label": "Webhook auth header name",
"description": "The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests. Must be 1-1000 characters and contain only ASCII letters, numbers, hyphens, and underscores. Requires `webhook_auth_header_value` and `webhook_url` to also be set.",
"type": [
"string",
"null"
]
},
"webhook_status_code": {
"x-label": "Webhook HTTP status code",
"description": "The status code we received from your server when delivering the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) request, if a webhook URL was provided",
"type": [
"integer",
"null"
]
},
"webhook_url": {
"x-label": "Webhook URL",
"description": "The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n",
"type": [
"string",
"null"
],
"format": "url"
},
"words": {
"x-label": "Words",
"description": "An array of temporally-sequential word objects, one for each word in the transcript.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Word",
"$ref": "#/components/schemas/TranscriptWord"
}
},
"unredacted_words": {
"x-label": "Unredacted words",
"description": "The original temporally-sequential word objects before PII redaction was applied. Same shape as `words`. Only returned when `redact_pii_return_unredacted` was set to `true` on the transcription request, otherwise this field is omitted and the `words` field remains fully redacted. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Word",
"$ref": "#/components/schemas/TranscriptWord"
}
},
"acoustic_model": {
"x-label": "Acoustic model",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "string",
"deprecated": true
},
"custom_topics": {
"x-label": "Custom topics enabled",
"description": "This parameter does not currently have any functionality attached to it.",
"type": [
"boolean",
"null"
],
"deprecated": true
},
"language_model": {
"x-label": "Language model",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "string",
"deprecated": true
},
"speech_model": {
"x-label": "Speech model",
"description": "This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n",
"oneOf": [
{
"$ref": "#/components/schemas/SpeechModel"
},
{
"type": "null"
}
],
"deprecated": true
},
"speed_boost": {
"x-label": "Speed boost",
"description": "This parameter does not currently have any functionality attached to it.",
"type": [
"boolean",
"null"
],
"deprecated": true
},
"topics": {
"x-label": "Topics",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "array",
"items": {
"x-label": "Topic",
"type": "string"
},
"deprecated": true
},
"translated_texts": {
"type": "object",
"description": "Translated text keyed by language code. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details.",
"properties": {
"language_code": {
"x-label": "Language code",
"type": "string",
"description": "Translated text for this language code"
}
}
}
},
"required": [
"id",
"speech_model",
"language_model",
"acoustic_model",
"status",
"audio_url",
"webhook_auth",
"auto_highlights",
"redact_pii",
"summarization",
"language_confidence_threshold",
"language_confidence"
],
"example": {
"id": "9ea68fd3-f953-42c1-9742-976c447fb463",
"speech_model": null,
"language_model": "assemblyai_default",
"acoustic_model": "assemblyai_default",
"language_code": "en_us",
"language_detection": true,
"language_confidence_threshold": 0.7,
"language_confidence": 0.9959,
"status": "completed",
"audio_url": "https://assembly.ai/wildfires.mp3",
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning. What is it about the conditions right now that have caused this round of wildfires to affect so many people so far away? Well, there's a couple of things. The season has been pretty dry already. And then the fact that we're getting hit in the US. Is because there's a couple of weather systems that are essentially channeling the smoke from those Canadian wildfires through Pennsylvania into the Mid Atlantic and the Northeast and kind of just dropping the smoke there. So what is it in this haze that makes it harmful? And I'm assuming it is harmful. It is. The levels outside right now in Baltimore are considered unhealthy. And most of that is due to what's called particulate matter, which are tiny particles, microscopic smaller than the width of your hair that can get into your lungs and impact your respiratory system, your cardiovascular system, and even your neurological your brain. What makes this particularly harmful? Is it the volume of particulant? Is it something in particular? What is it exactly? Can you just drill down on that a little bit more? Yeah. So the concentration of particulate matter I was looking at some of the monitors that we have was reaching levels of what are, in science, big 150 micrograms per meter cubed, which is more than ten times what the annual average should be and about four times higher than what you're supposed to have on a 24 hours average. And so the concentrations of these particles in the air are just much, much higher than we typically see. And exposure to those high levels can lead to a host of health problems. And who is most vulnerable? I noticed that in New York City, for example, they're canceling outdoor activities. And so here it is in the early days of summer, and they have to keep all the kids inside. So who tends to be vulnerable in a situation like this? It's the youngest. So children, obviously, whose bodies are still developing. The elderly, who are their bodies are more in decline and they're more susceptible to the health impacts of breathing, the poor air quality. And then people who have preexisting health conditions, people with respiratory conditions or heart conditions can be triggered by high levels of air pollution. Could this get worse? That's a good question. In some areas, it's much worse than others. And it just depends on kind of where the smoke is concentrated. I think New York has some of the higher concentrations right now, but that's going to change as that air moves away from the New York area. But over the course of the next few days, we will see different areas being hit at different times with the highest concentrations. I was going to ask you about more fires start burning. I don't expect the concentrations to go up too much higher. I was going to ask you how and you started to answer this, but how much longer could this last? Or forgive me if I'm asking you to speculate, but what do you think? Well, I think the fires are going to burn for a little bit longer, but the key for us in the US. Is the weather system changing. And so right now, it's kind of the weather systems that are pulling that air into our mid Atlantic and Northeast region. As those weather systems change and shift, we'll see that smoke going elsewhere and not impact us in this region as much. And so I think that's going to be the defining factor. And I think the next couple of days we're going to see a shift in that weather pattern and start to push the smoke away from where we are. And finally, with the impacts of climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences or circumstances? I mean, that is one of the predictions for climate change. Looking into the future, the fire season is starting earlier and lasting longer, and we're seeing more frequent fires. So, yeah, this is probably something that we'll be seeing more frequently. This tends to be much more of an issue in the Western US. So the eastern US. Getting hit right now is a little bit new. But yeah, I think with climate change moving forward, this is something that is going to happen more frequently. That's Peter De Carlo, associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Sergeant Carlo, thanks so much for joining us and sharing this expertise with us. Thank you for having me.",
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.97465,
"speaker": null
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 0.99999,
"speaker": null
},
{
"text": "hundreds",
"start": 1076,
"end": 1418,
"confidence": 0.99844,
"speaker": null
},
{
"text": "of",
"start": 1434,
"end": 1614,
"confidence": 0.84,
"speaker": null
},
{
"text": "wildfires",
"start": 1652,
"end": 2346,
"confidence": 0.89572,
"speaker": null
},
{
"text": "in",
"start": 2378,
"end": 2526,
"confidence": 0.99994,
"speaker": null
},
{
"text": "Canada",
"start": 2548,
"end": 3130,
"confidence": 0.93953,
"speaker": null
},
{
"text": "is",
"start": 3210,
"end": 3454,
"confidence": 0.999,
"speaker": null
},
{
"text": "triggering",
"start": 3492,
"end": 3946,
"confidence": 0.74794,
"speaker": null
},
{
"text": "air",
"start": 3978,
"end": 4174,
"confidence": 1,
"speaker": null
},
{
"text": "quality",
"start": 4212,
"end": 4558,
"confidence": 0.88077,
"speaker": null
},
{
"text": "alerts",
"start": 4644,
"end": 5114,
"confidence": 0.94814,
"speaker": null
},
{
"text": "throughout",
"start": 5162,
"end": 5466,
"confidence": 0.99726,
"speaker": null
},
{
"text": "the",
"start": 5498,
"end": 5694,
"confidence": 0.79,
"speaker": null
},
{
"text": "US.",
"start": 5732,
"end": 6382,
"confidence": 0.89,
"speaker": null
}
],
"utterances": [
{
"confidence": 0.9359033333333334,
"end": 26950,
"speaker": "A",
"start": 250,
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor.",
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.97503,
"speaker": "A"
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 0.99999,
"speaker": "A"
},
{
"text": "hundreds",
"start": 1076,
"end": 1418,
"confidence": 0.99843,
"speaker": "A"
},
{
"text": "of",
"start": 1434,
"end": 1614,
"confidence": 0.85,
"speaker": "A"
},
{
"text": "wildfires",
"start": 1652,
"end": 2346,
"confidence": 0.89657,
"speaker": "A"
},
{
"text": "in",
"start": 2378,
"end": 2526,
"confidence": 0.99994,
"speaker": "A"
},
{
"text": "Canada",
"start": 2548,
"end": 3130,
"confidence": 0.93864,
"speaker": "A"
},
{
"text": "is",
"start": 3210,
"end": 3454,
"confidence": 0.999,
"speaker": "A"
},
{
"text": "triggering",
"start": 3492,
"end": 3946,
"confidence": 0.75366,
"speaker": "A"
},
{
"text": "air",
"start": 3978,
"end": 4174,
"confidence": 1,
"speaker": "A"
},
{
"text": "quality",
"start": 4212,
"end": 4558,
"confidence": 0.87745,
"speaker": "A"
},
{
"text": "alerts",
"start": 4644,
"end": 5114,
"confidence": 0.94739,
"speaker": "A"
},
{
"text": "throughout",
"start": 5162,
"end": 5466,
"confidence": 0.99726,
"speaker": "A"
},
{
"text": "the",
"start": 5498,
"end": 5694,
"confidence": 0.79,
"speaker": "A"
},
{
"text": "US.",
"start": 5732,
"end": 6382,
"confidence": 0.88,
"speaker": "A"
}
]
}
],
"confidence": 0.9404651451800253,
"audio_duration": 281,
"punctuate": true,
"format_text": true,
"multichannel": false,
"webhook_url": "https://your-webhook-url.tld/path",
"webhook_status_code": 200,
"webhook_auth": true,
"webhook_auth_header_name": "webhook-secret",
"auto_highlights_result": {
"status": "success",
"results": [
{
"count": 1,
"rank": 0.08,
"text": "air quality alerts",
"timestamps": [
{
"start": 3978,
"end": 5114
}
]
},
{
"count": 1,
"rank": 0.08,
"text": "wide ranging air quality consequences",
"timestamps": [
{
"start": 235388,
"end": 238694
}
]
},
{
"count": 1,
"rank": 0.07,
"text": "more wildfires",
"timestamps": [
{
"start": 230972,
"end": 232354
}
]
},
{
"count": 1,
"rank": 0.07,
"text": "air pollution",
"timestamps": [
{
"start": 156004,
"end": 156910
}
]
},
{
"count": 3,
"rank": 0.07,
"text": "weather systems",
"timestamps": [
{
"start": 47344,
"end": 47958
},
{
"start": 205268,
"end": 205818
},
{
"start": 211588,
"end": 213434
}
]
},
{
"count": 2,
"rank": 0.06,
"text": "high levels",
"timestamps": [
{
"start": 121128,
"end": 121646
},
{
"start": 155412,
"end": 155866
}
]
},
{
"count": 1,
"rank": 0.06,
"text": "health conditions",
"timestamps": [
{
"start": 152138,
"end": 152666
}
]
},
{
"count": 2,
"rank": 0.06,
"text": "Peter de Carlo",
"timestamps": [
{
"start": 18948,
"end": 19930
},
{
"start": 268298,
"end": 269194
}
]
},
{
"count": 1,
"rank": 0.06,
"text": "New York City",
"timestamps": [
{
"start": 125768,
"end": 126274
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "respiratory conditions",
"timestamps": [
{
"start": 152964,
"end": 153786
}
]
},
{
"count": 3,
"rank": 0.05,
"text": "New York",
"timestamps": [
{
"start": 125768,
"end": 126034
},
{
"start": 171448,
"end": 171938
},
{
"start": 176008,
"end": 176322
}
]
},
{
"count": 3,
"rank": 0.05,
"text": "climate change",
"timestamps": [
{
"start": 229548,
"end": 230230
},
{
"start": 244576,
"end": 245162
},
{
"start": 263348,
"end": 263950
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "Johns Hopkins University Varsity",
"timestamps": [
{
"start": 23972,
"end": 25490
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "heart conditions",
"timestamps": [
{
"start": 153988,
"end": 154506
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "air quality warnings",
"timestamps": [
{
"start": 12308,
"end": 13434
}
]
}
]
},
"auto_highlights": true,
"audio_start_from": 10,
"audio_end_at": 280,
"filter_profanity": true,
"redact_pii": true,
"redact_pii_audio": true,
"redact_pii_audio_quality": "mp3",
"redact_pii_policies": [
"us_social_security_number",
"credit_card_number"
],
"redact_pii_sub": "hash",
"speaker_labels": true,
"content_safety": true,
"iab_categories": true,
"content_safety_labels": {
"status": "success",
"results": [
{
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
"labels": [
{
"label": "disasters",
"confidence": 0.8142836093902588,
"severity": 0.4093044400215149
}
],
"sentences_idx_start": 0,
"sentences_idx_end": 5,
"timestamp": {
"start": 250,
"end": 28840
}
}
],
"summary": {
"disasters": 0.9940800441842205,
"health_issues": 0.9216489289040967
},
"severity_score_summary": {
"disasters": {
"low": 0.5733263024656846,
"medium": 0.42667369753431533,
"high": 0
},
"health_issues": {
"low": 0.22863814977924785,
"medium": 0.45014154926938227,
"high": 0.32122030095136983
}
}
},
"iab_categories_result": {
"status": "success",
"results": [
{
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
"labels": [
{
"relevance": 0.988274097442627,
"label": "Home&Garden>IndoorEnvironmentalQuality"
},
{
"relevance": 0.5821335911750793,
"label": "NewsAndPolitics>Weather"
},
{
"relevance": 0.0042327106930315495,
"label": "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth"
},
{
"relevance": 0.0033971222583204508,
"label": "NewsAndPolitics>Disasters"
},
{
"relevance": 0.002469958271831274,
"label": "BusinessAndFinance>Business>GreenSolutions"
},
{
"relevance": 0.0014376690378412604,
"label": "MedicalHealth>DiseasesAndConditions>Cancer"
},
{
"relevance": 0.0014294233405962586,
"label": "Science>Environment"
},
{
"relevance": 0.001234519761055708,
"label": "Travel>TravelLocations>PolarTravel"
},
{
"relevance": 0.0010231725173071027,
"label": "MedicalHealth>DiseasesAndConditions>ColdAndFlu"
},
{
"relevance": 0.0007445293595083058,
"label": "BusinessAndFinance>Industries>PowerAndEnergyIndustry"
}
],
"timestamp": {
"start": 250,
"end": 28840
}
}
],
"summary": {
"NewsAndPolitics>Weather": 1,
"Home&Garden>IndoorEnvironmentalQuality": 0.9043831825256348,
"Science>Environment": 0.16117265820503235,
"BusinessAndFinance>Industries>EnvironmentalServicesIndustry": 0.14393523335456848,
"MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth": 0.11401086300611496,
"BusinessAndFinance>Business>GreenSolutions": 0.06348437070846558,
"NewsAndPolitics>Disasters": 0.05041387677192688,
"Travel>TravelLocations>PolarTravel": 0.01308488193899393,
"HealthyLiving": 0.008222488686442375,
"MedicalHealth>DiseasesAndConditions>ColdAndFlu": 0.0022315620444715023,
"MedicalHealth>DiseasesAndConditions>HeartAndCardiovascularDiseases": 0.00213034451007843,
"HealthyLiving>Wellness>SmokingCessation": 0.001540527562610805,
"MedicalHealth>DiseasesAndConditions>Injuries": 0.0013950627762824297,
"BusinessAndFinance>Industries>PowerAndEnergyIndustry": 0.0012570273829624057,
"MedicalHealth>DiseasesAndConditions>Cancer": 0.001097781932912767,
"MedicalHealth>DiseasesAndConditions>Allergies": 0.0010148967849090695,
"MedicalHealth>DiseasesAndConditions>MentalHealth": 0.000717321818228811,
"Style&Fashion>PersonalCare>DeodorantAndAntiperspirant": 0.0006022014422342181,
"Technology&Computing>Computing>ComputerNetworking": 0.0005461975233629346,
"MedicalHealth>DiseasesAndConditions>Injuries>FirstAid": 0.0004885646631009877
}
},
"custom_spelling": null,
"throttled": null,
"auto_chapters": false,
"summarization": false,
"summary_type": null,
"summary_model": null,
"custom_topics": true,
"topics": [],
"speech_threshold": 0.5,
"remove_audio_tags": null,
"domain": null,
"disfluencies": false,
"sentiment_analysis": true,
"sentiment_analysis_results": null,
"entity_detection": true,
"entities": [
{
"entity_type": "location",
"text": "Canada",
"start": 2548,
"end": 3130
},
{
"entity_type": "location",
"text": "the US",
"start": 5498,
"end": 6382
},
{
"entity_type": "location",
"text": "Maine",
"start": 7492,
"end": 7914
},
{
"entity_type": "location",
"text": "Maryland",
"start": 8212,
"end": 8634
},
{
"entity_type": "location",
"text": "Minnesota",
"start": 8932,
"end": 9578
},
{
"entity_type": "person_name",
"text": "Peter de Carlo",
"start": 18948,
"end": 19930
},
{
"entity_type": "occupation",
"text": "associate professor",
"start": 20292,
"end": 21194
},
{
"entity_type": "organization",
"text": "Department of Environmental Health and Engineering",
"start": 21508,
"end": 23706
},
{
"entity_type": "organization",
"text": "Johns Hopkins University Varsity",
"start": 23972,
"end": 25490
},
{
"entity_type": "occupation",
"text": "professor",
"start": 26076,
"end": 26950
},
{
"entity_type": "location",
"text": "the US",
"start": 45184,
"end": 45898
},
{
"entity_type": "nationality",
"text": "Canadian",
"start": 49728,
"end": 50086
}
],
"chapters": null,
"summary": null,
"speakers_expected": 2
}
},
"TopicDetectionModelResult": {
"x-label": "Topic Detection result",
"description": "The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.\n",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"required": [
"status",
"results",
"summary"
],
"properties": {
"status": {
"x-label": "Status",
"description": "The status of the Topic Detection model. Either success, or unavailable in the rare case that the model failed.",
"$ref": "#/components/schemas/AudioIntelligenceModelStatus"
},
"results": {
"x-label": "Results",
"description": "An array of results for the Topic Detection model",
"type": "array",
"items": {
"x-label": "Topic Detection result",
"$ref": "#/components/schemas/TopicDetectionResult"
}
},
"summary": {
"x-label": "Summary",
"description": "The overall relevance of topic to the entire audio file",
"type": "object",
"additionalProperties": {
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
}
}
},
"example": {
"status": "success",
"results": [
{
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
"labels": [
{
"relevance": 0.988274097442627,
"label": "Home&Garden>IndoorEnvironmentalQuality"
},
{
"relevance": 0.5821335911750793,
"label": "NewsAndPolitics>Weather"
},
{
"relevance": 0.0042327106930315495,
"label": "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth"
},
{
"relevance": 0.0033971222583204508,
"label": "NewsAndPolitics>Disasters"
},
{
"relevance": 0.002469958271831274,
"label": "BusinessAndFinance>Business>GreenSolutions"
},
{
"relevance": 0.0014376690378412604,
"label": "MedicalHealth>DiseasesAndConditions>Cancer"
},
{
"relevance": 0.0014294233405962586,
"label": "Science>Environment"
},
{
"relevance": 0.001234519761055708,
"label": "Travel>TravelLocations>PolarTravel"
},
{
"relevance": 0.0010231725173071027,
"label": "MedicalHealth>DiseasesAndConditions>ColdAndFlu"
},
{
"relevance": 0.0007445293595083058,
"label": "BusinessAndFinance>Industries>PowerAndEnergyIndustry"
}
],
"timestamp": {
"start": 250,
"end": 28840
}
}
],
"summary": {
"NewsAndPolitics>Weather": 1,
"Home&Garden>IndoorEnvironmentalQuality": 0.9043831825256348,
"Science>Environment": 0.16117265820503235,
"BusinessAndFinance>Industries>EnvironmentalServicesIndustry": 0.14393523335456848,
"MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth": 0.11401086300611496,
"BusinessAndFinance>Business>GreenSolutions": 0.06348437070846558,
"NewsAndPolitics>Disasters": 0.05041387677192688,
"Travel>TravelLocations>PolarTravel": 0.01308488193899393,
"HealthyLiving": 0.008222488686442375,
"MedicalHealth>DiseasesAndConditions>ColdAndFlu": 0.0022315620444715023,
"MedicalHealth>DiseasesAndConditions>HeartAndCardiovascularDiseases": 0.00213034451007843,
"HealthyLiving>Wellness>SmokingCessation": 0.001540527562610805,
"MedicalHealth>DiseasesAndConditions>Injuries": 0.0013950627762824297,
"BusinessAndFinance>Industries>PowerAndEnergyIndustry": 0.0012570273829624057,
"MedicalHealth>DiseasesAndConditions>Cancer": 0.001097781932912767,
"MedicalHealth>DiseasesAndConditions>Allergies": 0.0010148967849090695,
"MedicalHealth>DiseasesAndConditions>MentalHealth": 0.000717321818228811,
"Style&Fashion>PersonalCare>DeodorantAndAntiperspirant": 0.0006022014422342181,
"Technology&Computing>Computing>ComputerNetworking": 0.0005461975233629346,
"MedicalHealth>DiseasesAndConditions>Injuries>FirstAid": 0.0004885646631009877
}
}
},
"ContentSafetyLabelsResult": {
"x-label": "Content Moderation labels result",
"description": "An array of results for the Content Moderation model, if it is enabled.\nSee [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.\n",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"required": [
"status",
"results",
"summary",
"severity_score_summary"
],
"properties": {
"status": {
"x-label": "Status",
"description": "The status of the Content Moderation model. Either success, or unavailable in the rare case that the model failed.",
"$ref": "#/components/schemas/AudioIntelligenceModelStatus"
},
"results": {
"x-label": "Results",
"description": "An array of results for the Content Moderation model",
"type": "array",
"items": {
"x-label": "Content Moderation label result",
"$ref": "#/components/schemas/ContentSafetyLabelResult"
}
},
"summary": {
"x-label": "Summary",
"description": "A summary of the Content Moderation confidence results for the entire audio file",
"type": "object",
"additionalProperties": {
"description": "A confidence score for the presence of the sensitive topic \"topic\" across the entire audio file",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
}
},
"severity_score_summary": {
"x-label": "Severity score summary",
"description": "A summary of the Content Moderation severity results for the entire audio file",
"type": "object",
"additionalProperties": {
"$ref": "#/components/schemas/SeverityScoreSummary"
}
}
},
"example": {
"status": "success",
"results": [
{
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
"labels": [
{
"label": "disasters",
"confidence": 0.8142836093902588,
"severity": 0.4093044400215149
}
],
"sentences_idx_start": 0,
"sentences_idx_end": 5,
"timestamp": {
"start": 250,
"end": 28840
}
}
],
"summary": {
"disasters": 0.9940800441842205,
"health_issues": 0.9216489289040967
},
"severity_score_summary": {
"disasters": {
"low": 0.5733263024656846,
"medium": 0.42667369753431533,
"high": 0
},
"health_issues": {
"low": 0.22863814977924785,
"medium": 0.45014154926938227,
"high": 0.32122030095136983
}
}
}
},
"Chapter": {
"x-label": "Chapter",
"description": "Chapter of the audio file",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"required": [
"gist",
"headline",
"summary",
"start",
"end"
],
"properties": {
"gist": {
"x-label": "Gist",
"description": "An ultra-short summary (just a few words) of the content spoken in the chapter",
"type": "string"
},
"headline": {
"x-label": "Headline",
"description": "A single sentence summary of the content spoken during the chapter",
"type": "string"
},
"summary": {
"x-label": "Summary",
"description": "A one paragraph summary of the content spoken during the chapter",
"type": "string"
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, for the chapter",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The starting time, in milliseconds, for the chapter",
"type": "integer"
}
},
"example": {
"summary": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. In some places, the air quality warnings include the warning to stay inside.",
"gist": "Smoggy air quality alerts across US",
"headline": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts across US",
"start": 250,
"end": 28840
}
},
"Entity": {
"x-label": "Entity",
"description": "A detected entity",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"required": [
"entity_type",
"text",
"start",
"end"
],
"properties": {
"entity_type": {
"x-label": "Entity type",
"description": "The type of entity for the detected entity",
"$ref": "#/components/schemas/EntityType"
},
"text": {
"x-label": "Text",
"description": "The text for the detected entity",
"type": "string"
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, at which the detected entity appears in the audio file",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The ending time, in milliseconds, for the detected entity in the audio file",
"type": "integer"
}
},
"example": {
"entity_type": "location",
"text": "Canada",
"start": 2548,
"end": 3130
}
},
"EntityType": {
"x-label": "Entity type",
"description": "The type of entity for the detected entity. Entity Detection returns every location reference under the single `location` value; granular location subtypes (`location_address`, `location_city`, etc.) are supported only by PII redaction.",
"x-fern-sdk-group-name": "transcripts",
"type": "string",
"enum": [
"account_number",
"banking_information",
"blood_type",
"credit_card_cvv",
"credit_card_expiration",
"credit_card_number",
"date",
"date_interval",
"date_of_birth",
"drivers_license",
"drug",
"duration",
"email_address",
"event",
"filename",
"gender",
"gender_sexuality",
"healthcare_number",
"injury",
"ip_address",
"language",
"location",
"marital_status",
"medical_condition",
"medical_process",
"money_amount",
"nationality",
"number_sequence",
"occupation",
"organization",
"organization_medical_facility",
"passport_number",
"password",
"person_age",
"person_name",
"phone_number",
"physical_attribute",
"political_affiliation",
"religion",
"sexuality",
"statistics",
"time",
"url",
"us_social_security_number",
"username",
"vehicle_id",
"zodiac_sign"
],
"x-fern-enum": {
"account_number": {
"description": "Customer account or membership identification number (e.g., Policy No. 10042992, Member ID: HZ-5235-001)"
},
"banking_information": {
"description": "Banking information, including account and routing numbers"
},
"blood_type": {
"description": "Blood type (e.g., O-, AB positive)"
},
"credit_card_cvv": {
"description": "Credit card verification code (e.g., CVV: 080)"
},
"credit_card_expiration": {
"description": "Expiration date of a credit card"
},
"credit_card_number": {
"description": "Credit card number"
},
"date": {
"description": "Specific calendar date (e.g., December 18)"
},
"date_interval": {
"description": "Broader time periods, including date ranges, months, seasons, years, and decades (e.g., 2020-2021, 5-9 May, January 1984)"
},
"date_of_birth": {
"description": "Date of birth (e.g., Date of Birth: March 7,1961)"
},
"drivers_license": {
"description": "Driver's license number. (e.g., DL# 356933-540)"
},
"drug": {
"description": "Medications, vitamins, or supplements (e.g., Advil, Acetaminophen, Panadol)"
},
"duration": {
"description": "Measurements of time expressed as a numerical value plus a unit (e.g., 8 months, 2 years)"
},
"email_address": {
"description": "Email address (e.g., support@assemblyai.com)"
},
"event": {
"description": "Name of an event or holiday (e.g., Olympics, Yom Kippur)"
},
"filename": {
"description": "Names of computer files, including the extension or filepath (e.g., Taxes/2012/brad-tax-returns.pdf)"
},
"gender": {
"description": "Terms indicating gender identity (e.g., female, male, non-binary)"
},
"gender_sexuality": {
"description": "Terms indicating gender identity or sexual orientation, including slang terms (e.g., female, bisexual, trans)"
},
"healthcare_number": {
"description": "Healthcare numbers and health plan beneficiary numbers (e.g., Policy No.: 5584-486-674-YM)"
},
"injury": {
"description": "Bodily injury (e.g., I broke my arm, I have a sprained wrist)"
},
"ip_address": {
"description": "Internet IP address, including IPv4 and IPv6 formats (e.g., 192.168.0.1)"
},
"language": {
"description": "Name of a natural language (e.g., Spanish, French)"
},
"location": {
"description": "Any Location reference including mailing address, postal code, city, state, province, country, or coordinates. (e.g., Lake Victoria, 145 Windsor St., 90210)"
},
"marital_status": {
"description": "Terms indicating marital status (e.g., Single, common-law, ex-wife, married)"
},
"medical_condition": {
"description": "Name of a medical condition, disease, syndrome, deficit, or disorder (e.g., chronic fatigue syndrome, arrhythmia, depression)"
},
"medical_process": {
"description": "Medical process, including treatments, procedures, and tests (e.g., heart surgery, CT scan)"
},
"money_amount": {
"description": "Name and/or amount of currency (e.g., 15 pesos, $94.50)"
},
"nationality": {
"description": "Terms indicating nationality, ethnicity, or race (e.g., American, Asian, Caucasian)"
},
"number_sequence": {
"description": "Numerical PII (including alphanumeric strings) that doesn't fall under other categories"
},
"occupation": {
"description": "Job title or profession (e.g., professor, actors, engineer, CPA)"
},
"organization": {
"description": "Name of an organization (e.g., CNN, McDonalds, University of Alaska, Northwest General Hospital)"
},
"organization_medical_facility": {
"description": "Name of a medical facility (e.g., Mayo Clinic, Northwest General Hospital)"
},
"passport_number": {
"description": "Passport numbers, issued by any country (e.g., PA4568332, NU3C6L86S12)"
},
"password": {
"description": "Account passwords, PINs, access keys, or verification answers (e.g., 27%alfalfa, temp1234, My mother's maiden name is Smith)"
},
"person_age": {
"description": "Number associated with an age (e.g., 27, 75)"
},
"person_name": {
"description": "Name of a person (e.g., Bob, Doug Jones, Dr. Kay Martinez, MD)"
},
"phone_number": {
"description": "Telephone or fax number"
},
"physical_attribute": {
"description": "Distinctive bodily attributes, including race (e.g., I'm 190cm tall, He belongs to the Black students' association)"
},
"political_affiliation": {
"description": "Terms referring to a political party, movement, or ideology (e.g., Republican, Liberal)"
},
"religion": {
"description": "Terms indicating religious affiliation (e.g., Hindu, Catholic)"
},
"sexuality": {
"description": "Terms indicating sexual orientation (e.g., heterosexual, bisexual, gay)"
},
"statistics": {
"description": "Medical statistics (e.g., 18%, 18 percent)"
},
"time": {
"description": "Expressions indicating clock times (e.g., 19:37:28, 10pm EST)"
},
"url": {
"description": "Internet addresses (e.g., https://www.assemblyai.com/)"
},
"us_social_security_number": {
"description": "Social Security Number or equivalent"
},
"username": {
"description": "Usernames, login names, or handles (e.g., @AssemblyAI)"
},
"vehicle_id": {
"description": "Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers (e.g., 5FNRL38918B111818, BIF7547)"
},
"zodiac_sign": {
"description": "Names of Zodiac signs (e.g., Aries, Taurus)"
}
},
"x-aai-enum": {
"account_number": {
"label": "Account number"
},
"banking_information": {
"label": "Banking information"
},
"blood_type": {
"label": "Blood type"
},
"credit_card_cvv": {
"label": "Credit card CVV"
},
"credit_card_expiration": {
"label": "Credit card expiration"
},
"credit_card_number": {
"label": "Credit card number"
},
"date": {
"label": "Date"
},
"date_interval": {
"label": "Date interval"
},
"date_of_birth": {
"label": "Date of birth"
},
"drivers_license": {
"label": "Driver's license"
},
"drug": {
"label": "Drug"
},
"duration": {
"label": "Duration"
},
"email_address": {
"label": "Email address"
},
"event": {
"label": "Event"
},
"filename": {
"label": "Filename"
},
"gender": {
"label": "Gender"
},
"gender_sexuality": {
"label": "Gender sexuality"
},
"healthcare_number": {
"label": "Healthcare number"
},
"injury": {
"label": "Injury"
},
"ip_address": {
"label": "IP address"
},
"language": {
"label": "Language"
},
"location": {
"label": "Location"
},
"marital_status": {
"label": "Marital status"
},
"medical_condition": {
"label": "Medical condition"
},
"medical_process": {
"label": "Medical process"
},
"money_amount": {
"label": "Money amount"
},
"nationality": {
"label": "Nationality"
},
"number_sequence": {
"label": "Number sequence"
},
"occupation": {
"label": "Occupation"
},
"organization": {
"label": "Organization"
},
"organization_medical_facility": {
"label": "Organization medical facility"
},
"passport_number": {
"label": "Passport number"
},
"password": {
"label": "Password"
},
"person_age": {
"label": "Person age"
},
"person_name": {
"label": "Person name"
},
"phone_number": {
"label": "Phone number"
},
"physical_attribute": {
"label": "Physical attribute"
},
"political_affiliation": {
"label": "Political affiliation"
},
"religion": {
"label": "Religion"
},
"sexuality": {
"label": "Sexuality"
},
"statistics": {
"label": "Statistics"
},
"time": {
"label": "Time"
},
"url": {
"label": "URL"
},
"us_social_security_number": {
"label": "US Social Security Number"
},
"username": {
"label": "Username"
},
"vehicle_id": {
"label": "Vehicle ID"
},
"zodiac_sign": {
"label": "Zodiac sign"
}
}
},
"SentimentAnalysisResult": {
"x-label": "Sentiment Analysis result",
"description": "The result of the Sentiment Analysis model",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"required": [
"text",
"start",
"end",
"sentiment",
"confidence",
"speaker"
],
"properties": {
"text": {
"x-label": "Text",
"description": "The transcript of the sentence",
"type": "string"
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, of the sentence",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The ending time, in milliseconds, of the sentence",
"type": "integer"
},
"sentiment": {
"x-label": "Sentiment",
"description": "The detected sentiment for the sentence, one of POSITIVE, NEUTRAL, NEGATIVE",
"$ref": "#/components/schemas/Sentiment"
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the detected sentiment of the sentence, from 0 to 1",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"channel": {
"x-label": "Channel",
"description": "The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.",
"type": [
"string",
"null"
]
},
"speaker": {
"x-label": "Speaker",
"description": "The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null",
"type": [
"string",
"null"
]
}
},
"example": {
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US.",
"start": 250,
"end": 6350,
"sentiment": "NEGATIVE",
"confidence": 0.8181032538414001,
"speaker": null
}
},
"Sentiment": {
"x-label": "Sentiment",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"POSITIVE",
"NEUTRAL",
"NEGATIVE"
],
"x-aai-enum": {
"POSITIVE": {
"label": "Positive"
},
"NEUTRAL": {
"label": "Neutral"
},
"NEGATIVE": {
"label": "Negative"
}
}
},
"TopicDetectionResult": {
"x-label": "Topic detection result",
"description": "The result of the topic detection model",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"required": [
"text"
],
"properties": {
"text": {
"x-label": "Text",
"description": "The text in the transcript in which a detected topic occurs",
"type": "string"
},
"labels": {
"x-label": "Labels",
"description": "An array of detected topics in the text",
"type": "array",
"items": {
"x-label": "Label",
"type": "object",
"additionalProperties": false,
"required": [
"relevance",
"label"
],
"properties": {
"relevance": {
"x-label": "Relevance",
"description": "How relevant the detected topic is of a detected topic",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"label": {
"x-label": "Label",
"description": "The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship",
"type": "string"
}
}
}
},
"timestamp": {
"x-label": "Timestamp",
"$ref": "#/components/schemas/Timestamp"
}
},
"example": {
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
"labels": [
{
"relevance": 0.988274097442627,
"label": "Home&Garden>IndoorEnvironmentalQuality"
},
{
"relevance": 0.5821335911750793,
"label": "NewsAndPolitics>Weather"
},
{
"relevance": 0.0042327106930315495,
"label": "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth"
},
{
"relevance": 0.0033971222583204508,
"label": "NewsAndPolitics>Disasters"
},
{
"relevance": 0.002469958271831274,
"label": "BusinessAndFinance>Business>GreenSolutions"
},
{
"relevance": 0.0014376690378412604,
"label": "MedicalHealth>DiseasesAndConditions>Cancer"
},
{
"relevance": 0.0014294233405962586,
"label": "Science>Environment"
},
{
"relevance": 0.001234519761055708,
"label": "Travel>TravelLocations>PolarTravel"
},
{
"relevance": 0.0010231725173071027,
"label": "MedicalHealth>DiseasesAndConditions>ColdAndFlu"
},
{
"relevance": 0.0007445293595083058,
"label": "BusinessAndFinance>Industries>PowerAndEnergyIndustry"
}
],
"timestamp": {
"start": 250,
"end": 28840
}
}
},
"ContentSafetyLabel": {
"x-label": "Content Moderation label",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"label",
"confidence",
"severity"
],
"properties": {
"label": {
"x-label": "Label",
"description": "The label of the sensitive topic",
"type": "string"
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the topic being discussed, from 0 to 1",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"severity": {
"x-label": "Severity",
"description": "How severely the topic is discussed in the section, from 0 to 1",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
}
},
"example": {
"label": "disasters",
"confidence": 0.8142836093902588,
"severity": 0.4093044400215149
}
},
"ContentSafetyLabelResult": {
"x-label": "Content Moderation label result",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"text",
"labels",
"sentences_idx_start",
"sentences_idx_end",
"timestamp"
],
"properties": {
"text": {
"x-label": "Text",
"description": "The transcript of the section flagged by the Content Moderation model",
"type": "string"
},
"labels": {
"x-label": "Labels",
"description": "An array of safety labels, one per sensitive topic that was detected in the section",
"type": "array",
"items": {
"x-label": "Label",
"$ref": "#/components/schemas/ContentSafetyLabel"
}
},
"sentences_idx_start": {
"x-label": "Sentence index start",
"description": "The sentence index at which the section begins",
"type": "integer"
},
"sentences_idx_end": {
"x-label": "Sentence index end",
"description": "The sentence index at which the section ends",
"type": "integer"
},
"timestamp": {
"x-label": "Timestamp",
"description": "Timestamp information for the section",
"$ref": "#/components/schemas/Timestamp"
}
},
"example": {
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
"labels": [
{
"label": "disasters",
"confidence": 0.8142836093902588,
"severity": 0.4093044400215149
}
],
"sentences_idx_start": 0,
"sentences_idx_end": 5,
"timestamp": {
"start": 250,
"end": 28840
}
}
},
"SeverityScoreSummary": {
"x-label": "Severity score summary",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"required": [
"low",
"medium",
"high"
],
"properties": {
"low": {
"x-label": "Low",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"medium": {
"x-label": "Medium",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"high": {
"x-label": "High",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
}
},
"example": {
"low": 0.5733263024656846,
"medium": 0.42667369753431533,
"high": 0
}
},
"AutoHighlightsResult": {
"x-label": "Auto highlights result",
"description": "An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.\n",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"required": [
"status",
"results"
],
"properties": {
"status": {
"x-label": "Status",
"description": "The status of the Key Phrases model. Either success, or unavailable in the rare case that the model failed.",
"$ref": "#/components/schemas/AudioIntelligenceModelStatus"
},
"results": {
"x-label": "Results",
"description": "A temporally-sequential array of Key Phrases",
"type": "array",
"items": {
"x-label": "Auto highlight result",
"$ref": "#/components/schemas/AutoHighlightResult"
}
}
},
"example": {
"status": "success",
"results": [
{
"count": 1,
"rank": 0.08,
"text": "air quality alerts",
"timestamps": [
{
"start": 3978,
"end": 5114
}
]
},
{
"count": 1,
"rank": 0.08,
"text": "wide ranging air quality consequences",
"timestamps": [
{
"start": 235388,
"end": 238694
}
]
},
{
"count": 1,
"rank": 0.07,
"text": "more wildfires",
"timestamps": [
{
"start": 230972,
"end": 232354
}
]
},
{
"count": 1,
"rank": 0.07,
"text": "air pollution",
"timestamps": [
{
"start": 156004,
"end": 156910
}
]
},
{
"count": 3,
"rank": 0.07,
"text": "weather systems",
"timestamps": [
{
"start": 47344,
"end": 47958
},
{
"start": 205268,
"end": 205818
},
{
"start": 211588,
"end": 213434
}
]
},
{
"count": 2,
"rank": 0.06,
"text": "high levels",
"timestamps": [
{
"start": 121128,
"end": 121646
},
{
"start": 155412,
"end": 155866
}
]
},
{
"count": 1,
"rank": 0.06,
"text": "health conditions",
"timestamps": [
{
"start": 152138,
"end": 152666
}
]
},
{
"count": 2,
"rank": 0.06,
"text": "Peter de Carlo",
"timestamps": [
{
"start": 18948,
"end": 19930
},
{
"start": 268298,
"end": 269194
}
]
},
{
"count": 1,
"rank": 0.06,
"text": "New York City",
"timestamps": [
{
"start": 125768,
"end": 126274
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "respiratory conditions",
"timestamps": [
{
"start": 152964,
"end": 153786
}
]
},
{
"count": 3,
"rank": 0.05,
"text": "New York",
"timestamps": [
{
"start": 125768,
"end": 126034
},
{
"start": 171448,
"end": 171938
},
{
"start": 176008,
"end": 176322
}
]
},
{
"count": 3,
"rank": 0.05,
"text": "climate change",
"timestamps": [
{
"start": 229548,
"end": 230230
},
{
"start": 244576,
"end": 245162
},
{
"start": 263348,
"end": 263950
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "Johns Hopkins University Varsity",
"timestamps": [
{
"start": 23972,
"end": 25490
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "heart conditions",
"timestamps": [
{
"start": 153988,
"end": 154506
}
]
},
{
"count": 1,
"rank": 0.05,
"text": "air quality warnings",
"timestamps": [
{
"start": 12308,
"end": 13434
}
]
}
]
}
},
"AutoHighlightResult": {
"x-label": "Auto highlight result",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"count",
"rank",
"text",
"timestamps"
],
"properties": {
"count": {
"x-label": "Count",
"description": "The total number of times the key phrase appears in the audio file",
"type": "integer"
},
"rank": {
"x-label": "Rank",
"description": "The total relevancy to the overall audio file of this key phrase - a greater number means more relevant",
"type": "number",
"format": "float",
"minimum": 0,
"maximum": 1
},
"text": {
"x-label": "Text",
"description": "The text itself of the key phrase",
"type": "string"
},
"timestamps": {
"x-label": "Timestamps",
"description": "The timestamp of the of the key phrase",
"type": "array",
"items": {
"x-label": "Timestamp",
"$ref": "#/components/schemas/Timestamp"
}
}
},
"example": {
"count": 1,
"rank": 0.08,
"text": "air quality alerts",
"timestamps": [
{
"start": 3978,
"end": 5114
}
]
}
},
"TranscriptWord": {
"x-label": "Word",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"confidence",
"start",
"end",
"text",
"speaker"
],
"properties": {
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript of this word",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, for the word",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The ending time, in milliseconds, for the word",
"type": "integer"
},
"text": {
"x-label": "Text",
"description": "The text of the word",
"type": "string"
},
"channel": {
"x-label": "Channel",
"description": "The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.",
"type": [
"string",
"null"
]
},
"speaker": {
"x-label": "Speaker",
"description": "The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null",
"type": [
"string",
"null"
]
}
},
"example": {
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.97465,
"channel": null,
"speaker": null
}
},
"TranscriptSentence": {
"x-label": "Sentence",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"text",
"start",
"end",
"confidence",
"words",
"speaker"
],
"properties": {
"text": {
"x-label": "Text",
"description": "The transcript of the sentence",
"type": "string"
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, for the sentence",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The ending time, in milliseconds, for the sentence",
"type": "integer"
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript of this sentence",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"words": {
"x-label": "Words",
"description": "An array of words in the sentence",
"type": "array",
"items": {
"x-label": "Word",
"$ref": "#/components/schemas/TranscriptWord"
}
},
"channel": {
"x-label": "Channel",
"description": "The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.",
"type": [
"string",
"null"
]
},
"speaker": {
"x-label": "Speaker",
"description": "The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null",
"type": [
"string",
"null"
]
}
},
"example": {
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US.",
"start": 250,
"end": 6350,
"confidence": 0.72412,
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.72412,
"speaker": null
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 0.99996,
"speaker": null
},
{
"text": "hundreds",
"start": 1076,
"end": 1466,
"confidence": 0.99992,
"speaker": null
},
{
"text": "of",
"start": 1498,
"end": 1646,
"confidence": 1,
"speaker": null
}
],
"speaker": null
}
},
"SentencesResponse": {
"x-label": "Sentences response",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"id",
"confidence",
"audio_duration",
"sentences"
],
"properties": {
"id": {
"x-label": "Transcript ID",
"description": "The unique identifier for the transcript",
"type": "string",
"format": "uuid"
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"audio_duration": {
"x-label": "Audio duration",
"description": "The duration of the audio file in seconds",
"type": "number"
},
"sentences": {
"x-label": "Sentences",
"description": "An array of sentences in the transcript",
"type": "array",
"items": {
"x-label": "Sentence",
"$ref": "#/components/schemas/TranscriptSentence"
}
}
},
"example": {
"sentences": [
{
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US.",
"start": 250,
"end": 6350,
"confidence": 0.72412,
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.72412,
"speaker": null
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 0.99996,
"speaker": null
},
{
"text": "hundreds",
"start": 1076,
"end": 1466,
"confidence": 0.99992,
"speaker": null
},
{
"text": "of",
"start": 1498,
"end": 1646,
"confidence": 1,
"speaker": null
}
],
"speaker": null
},
{
"text": "Skylines from Maine to Maryland to Minnesota are gray and smoggy.",
"start": 6500,
"end": 11050,
"confidence": 0.99819,
"words": [
{
"text": "Skylines",
"start": 6500,
"end": 7306,
"confidence": 0.99819,
"speaker": null
},
{
"text": "from",
"start": 7338,
"end": 7534,
"confidence": 0.99987,
"speaker": null
},
{
"text": "Maine",
"start": 7572,
"end": 7962,
"confidence": 0.9972,
"speaker": null
},
{
"text": "to",
"start": 8026,
"end": 8206,
"confidence": 1,
"speaker": null
},
{
"text": "Maryland",
"start": 8228,
"end": 8650,
"confidence": 0.5192,
"speaker": null
},
{
"text": "to",
"start": 8730,
"end": 8926,
"confidence": 1,
"speaker": null
}
],
"speaker": null
}
],
"id": "d5a3d302-066e-43fb-b63b-8f57baf185db",
"confidence": 0.9579390654205628,
"audio_duration": 281
}
},
"TranscriptParagraph": {
"x-label": "Paragraph",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"text",
"start",
"end",
"confidence",
"words"
],
"properties": {
"text": {
"x-label": "Text",
"description": "The transcript of the paragraph",
"type": "string"
},
"start": {
"x-label": "Start",
"description": "The starting time, in milliseconds, of the paragraph",
"type": "integer"
},
"end": {
"x-label": "End",
"description": "The ending time, in milliseconds, of the paragraph",
"type": "integer"
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript of this paragraph",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"words": {
"x-label": "Words",
"description": "An array of words in the paragraph",
"type": "array",
"items": {
"x-label": "Word",
"$ref": "#/components/schemas/TranscriptWord"
}
}
},
"example": {
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter Decarlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Good morning, professor.",
"start": 250,
"end": 26950,
"confidence": 0.73033,
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.73033,
"speaker": null
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 1,
"speaker": null
},
{
"text": "hundreds",
"start": 1076,
"end": 1466,
"confidence": 0.99992,
"speaker": null
},
{
"text": "of",
"start": 1498,
"end": 1646,
"confidence": 1,
"speaker": null
}
]
}
},
"ParagraphsResponse": {
"x-label": "Paragraphs response",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"id",
"confidence",
"audio_duration",
"paragraphs"
],
"properties": {
"id": {
"x-label": "Transcript ID",
"description": "The unique identifier of your transcript",
"type": "string",
"format": "uuid"
},
"confidence": {
"x-label": "Confidence",
"description": "The confidence score for the transcript",
"type": "number",
"format": "double",
"minimum": 0,
"maximum": 1
},
"audio_duration": {
"x-label": "Audio duration",
"description": "The duration of the audio file in seconds",
"type": "number"
},
"paragraphs": {
"x-label": "Paragraphs",
"description": "An array of paragraphs in the transcript",
"type": "array",
"items": {
"x-label": "Paragraph",
"$ref": "#/components/schemas/TranscriptParagraph"
}
}
},
"example": {
"paragraphs": [
{
"text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter Decarlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Good morning, professor.",
"start": 250,
"end": 26950,
"confidence": 0.73033,
"words": [
{
"text": "Smoke",
"start": 250,
"end": 650,
"confidence": 0.73033,
"speaker": null
},
{
"text": "from",
"start": 730,
"end": 1022,
"confidence": 1,
"speaker": null
},
{
"text": "hundreds",
"start": 1076,
"end": 1466,
"confidence": 0.99992,
"speaker": null
},
{
"text": "of",
"start": 1498,
"end": 1646,
"confidence": 1,
"speaker": null
}
]
},
{
"text": "Good morning. So what is it about the conditions right now that have caused this round of wildfires to affect so many people so far away? Well, there's a couple of things. The season has been pretty dry already, and then the fact that we're getting hit in the US. Is because there's a couple of weather systems that are essentially channeling the smoke from those Canadian wildfires through Pennsylvania into the Mid Atlantic and the Northeast and kind of just dropping the smoke there.",
"start": 27850,
"end": 56190,
"confidence": 0.99667,
"words": [
{
"text": "Good",
"start": 27850,
"end": 28262,
"confidence": 0.99667,
"speaker": null
},
{
"text": "morning.",
"start": 28316,
"end": 28920,
"confidence": 0.99742,
"speaker": null
},
{
"text": "So",
"start": 29290,
"end": 29702,
"confidence": 0.94736,
"speaker": null
}
]
}
],
"id": "d5a3d302-066e-43fb-b63b-8f57baf185db",
"confidence": 0.9578730257009361,
"audio_duration": 281
}
},
"PageDetails": {
"x-label": "Page details",
"description": "Details of the transcript page. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"limit",
"result_count",
"current_url",
"prev_url",
"next_url"
],
"properties": {
"limit": {
"x-label": "Limit",
"description": "The number of results this page is limited to",
"type": "integer"
},
"result_count": {
"x-label": "Result count",
"description": "The actual number of results in the page",
"type": "integer"
},
"current_url": {
"x-label": "Current URL",
"description": "The URL used to retrieve the current page of transcripts",
"type": "string",
"format": "url"
},
"prev_url": {
"x-label": "Previous URL",
"description": "The URL to the next page of transcripts. The previous URL always points to a page with older transcripts.",
"type": [
"string",
"null"
],
"format": "url"
},
"next_url": {
"x-label": "Next URL",
"description": "The URL to the next page of transcripts. The next URL always points to a page with newer transcripts.",
"type": [
"string",
"null"
],
"format": "url"
}
},
"example": {
"limit": 10,
"result_count": 10,
"current_url": "https://api.assemblyai.com/v2/transcript?limit=10",
"prev_url": "https://api.assemblyai.com/v2/transcript?limit=10&before_id=62npeahu2b-a8ea-4112-854c-69542c20d90c",
"next_url": "https://api.assemblyai.com/v2/transcript?limit=10&after_id=62nfw3mlar-01ad-4631-92f6-629929496eed"
}
},
"TranscriptListItem": {
"x-label": "Transcript list item",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"id",
"resource_url",
"status",
"created",
"completed",
"audio_url",
"error"
],
"properties": {
"id": {
"x-label": "ID",
"description": "The unique identifier for the transcript",
"type": "string",
"format": "uuid"
},
"resource_url": {
"x-label": "Resource URL",
"description": "The URL to retrieve the transcript",
"type": "string",
"format": "url"
},
"status": {
"x-label": "Status",
"description": "The status of the transcript",
"$ref": "#/components/schemas/TranscriptStatus"
},
"created": {
"x-label": "Created",
"description": "The date and time the transcript was created",
"type": "string",
"pattern": "^(?:(\\d{4}-\\d{2}-\\d{2})T(\\d{2}:\\d{2}:\\d{2}(?:\\.\\d+)?))$",
"x-fern-type": "datetime",
"x-ts-type": "Date"
},
"completed": {
"x-label": "Completed",
"description": "The date and time the transcript was completed",
"type": [
"string",
"null"
],
"pattern": "^(?:(\\d{4}-\\d{2}-\\d{2})T(\\d{2}:\\d{2}:\\d{2}(?:\\.\\d+)?))$",
"x-fern-type": "optional",
"x-ts-type": "Date | null"
},
"audio_url": {
"x-label": "Audio URL",
"description": "The URL to the audio file",
"type": "string",
"format": "url"
},
"error": {
"x-label": "Error",
"description": "Error message of why the transcript failed",
"type": [
"string",
"null"
]
}
},
"example": {
"id": "9ea68fd3-f953-42c1-9742-976c447fb463",
"resource_url": "https://api.assemblyai.com/v2/transcript/9ea68fd3-f953-42c1-9742-976c447fb463",
"status": "completed",
"created": "2023-11-02T21:49:25.586965",
"completed": "2023-11-02T21:49:25.586965",
"audio_url": "https://assembly.ai/wildfires.mp3",
"error": null
}
},
"TranscriptList": {
"x-label": "Transcript list",
"description": "A list of transcripts. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.",
"type": "object",
"x-fern-sdk-group-name": "transcripts",
"additionalProperties": false,
"required": [
"page_details",
"transcripts"
],
"properties": {
"page_details": {
"x-label": "Page details",
"description": "Details of the transcript page",
"$ref": "#/components/schemas/PageDetails"
},
"transcripts": {
"x-label": "Transcripts",
"description": "An array of transcripts",
"type": "array",
"items": {
"x-label": "Transcript list item",
"$ref": "#/components/schemas/TranscriptListItem"
}
}
},
"example": {
"page_details": {
"limit": 3,
"result_count": 3,
"current_url": "https://api.assemblyai.com/v2/transcript?limit=3",
"prev_url": "https://api.assemblyai.com/v2/transcript?limit=3&before_id=28a73d01-98db-41dd-9e98-2533ba0af117",
"next_url": "https://api.assemblyai.com/v2/transcript?limit=3&after_id=b33f4691-85b7-4f31-be12-a87cef1c1229"
},
"transcripts": [
{
"id": "b33f4691-85b7-4f31-be12-a87cef1c1229",
"resource_url": "https://api.assemblyai.com/v2/transcript/b33f4691-85b7-4f31-be12-a87cef1c1229",
"status": "completed",
"created": "2024-03-11T21:29:59.936851",
"completed": "2024-03-11T21:30:07.314223",
"audio_url": "http://deleted_by_user",
"error": null
},
{
"id": "ce522f10-d204-42e8-a838-6b95098145cc",
"resource_url": "https://api.assemblyai.com/v2/transcript/ce522f10-d204-42e8-a838-6b95098145cc",
"status": "error",
"created": "2024-03-11T21:23:59.979420",
"completed": null,
"audio_url": "https://storage.googleapis.com/client-docs-samples/nbc.oopsie",
"error": "Download error, unable to download https://storage.googleapis.com/client-docs-samples/nbc.oopsie. Please make sure the file exists and is accessible from the internet."
},
{
"id": "28a73d01-98db-41dd-9e98-2533ba0af117",
"resource_url": "https://api.assemblyai.com/v2/transcript/28a73d01-98db-41dd-9e98-2533ba0af117",
"status": "completed",
"created": "2024-03-11T21:12:57.372215",
"completed": "2024-03-11T21:13:03.267020",
"audio_url": "https://assembly.ai/nbc.mp3",
"error": null
}
]
}
},
"UploadedFile": {
"x-label": "Uploaded file",
"type": "object",
"x-fern-sdk-group-name": "files",
"additionalProperties": false,
"required": [
"upload_url"
],
"properties": {
"upload_url": {
"x-label": "Uploaded file URL",
"description": "A URL that points to your audio file, accessible only by AssemblyAI's servers\n",
"type": "string",
"format": "url"
}
},
"example": {
"upload_url": "https://cdn.assemblyai.com/upload/f756988d-47e2-4ca3-96ce-04bb168f8f2a"
}
},
"AudioIntelligenceModelStatus": {
"x-label": "Audio intelligence model status",
"x-fern-sdk-group-name": "transcripts",
"type": "string",
"description": "Either success, or unavailable in the rare case that the model failed",
"enum": [
"success",
"unavailable"
],
"x-aai-enum": {
"success": {
"label": "Success"
},
"unavailable": {
"label": "Unavailable"
}
}
},
"Error": {
"x-label": "Error",
"type": "object",
"additionalProperties": true,
"required": [
"error"
],
"properties": {
"error": {
"x-label": "Error message",
"description": "Error message",
"type": "string"
},
"status": {
"x-label": "Status",
"type": "string",
"const": "error"
}
},
"example": {
"error": "Transcript creation error, audio_url not found"
}
},
"TranslationRequestBody": {
"x-label": "Translation request body",
"description": "Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation).",
"type": "object",
"properties": {
"translation": {
"type": "object",
"properties": {
"target_languages": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of target language codes (e.g., `[\"es\", \"de\"]`). See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for supported languages."
},
"formal": {
"type": "boolean",
"description": "Use formal language style. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details.",
"default": true
},
"match_original_utterance": {
"type": "boolean",
"description": "When enabled with Speaker Labels, returns translated text in the utterances array. Each utterance will include a `translated_texts` key containing translations for each target language.",
"default": false
}
},
"required": [
"target_languages"
]
}
},
"required": [
"translation"
]
},
"SpeakerIdentificationRequestBody": {
"type": "object",
"description": "Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification).",
"properties": {
"speaker_identification": {
"type": "object",
"properties": {
"speaker_type": {
"type": "string",
"enum": [
"role",
"name"
],
"description": "Type of speaker identification. See [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) for details on each type."
},
"known_values": {
"type": "array",
"items": {
"type": "string"
},
"description": "Required if speaker_type is \"role\". Each value must be 35 characters or less."
},
"speakers": {
"type": "array",
"description": "An array of speaker objects with metadata to improve identification accuracy. Each object should include a `role` or `name` (depending on `speaker_type`) and an optional `description` to help the model identify the speaker. You can also include any additional custom properties (e.g., `company`, `title`) to provide more context. Use this as an alternative to `known_values` when you want to provide additional context about each speaker.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "The role of the speaker. Required when `speaker_type` is \"role\"."
},
"name": {
"type": "string",
"description": "The name of the speaker. Required when `speaker_type` is \"name\"."
},
"description": {
"type": "string",
"description": "A description of the speaker to help the model identify them based on conversational context."
}
},
"additionalProperties": true
}
}
},
"required": [
"speaker_type"
]
}
},
"required": [
"speaker_identification"
]
},
"CustomFormattingRequestBody": {
"type": "object",
"description": "Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting).",
"properties": {
"custom_formatting": {
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "Date format pattern (e.g., `\"mm/dd/yyyy\"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details."
},
"phone_number": {
"type": "string",
"description": "Phone number format pattern (e.g., `\"(xxx)xxx-xxxx\"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details."
},
"email": {
"type": "string",
"description": "Email format pattern (e.g., `\"username@domain.com\"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details."
}
}
}
},
"required": [
"custom_formatting"
]
},
"SummarizationRequestBody": {
"type": "object",
"description": "Request body for [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization).",
"properties": {
"summariazation": {
"type": "object",
"properties": {
"summary_type": {
"type": "string",
"enum": [
"paragraph",
"bullets"
],
"description": "Type of summary. Bullets returns short bullet point style summaries, paragraph is generally more verbose and detailed."
},
"effort": {
"type": "string",
"enum": [
"low",
"medium"
]
}
}
}
},
"required": [
"summarization"
]
},
"ActionItemsRequestBody": {
"type": "object",
"description": "Request body for [Action Items](https://www.assemblyai.com/docs/speech-understanding/action-items).",
"properties": {
"action_items": {
"type": "object",
"properties": {
"include_decisions": {
"type": "bool",
"description": "Option to include decision making in action items."
},
"effort": {
"type": "string",
"enum": [
"low",
"medium"
]
}
}
}
},
"required": [
"action_items"
]
},
"TranslationResponse": {
"type": "object",
"properties": {
"translation": {
"type": "object",
"properties": {
"status": {
"type": "string"
}
}
}
}
},
"SpeakerIdentificationResponse": {
"type": "object",
"properties": {
"speaker_identification": {
"type": "object",
"properties": {
"mapping": {
"type": "object",
"description": "A mapping of the original generic speaker labels (e.g., \"A\", \"B\") to the identified speaker names or roles.",
"additionalProperties": {
"type": "string"
}
},
"status": {
"type": "string"
}
}
}
}
},
"CustomFormattingResponse": {
"type": "object",
"properties": {
"custom_formatting": {
"type": "object",
"properties": {
"mapping": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"formatted_text": {
"type": "string"
}
}
}
}
},
"SummarizationResponse": {
"type": "object",
"properties": {
"summarization": {
"type": "object",
"properties": {
"summary": {
"type": "array",
"items": {
"type": "object"
}
},
"status": {
"type": "string"
}
}
},
"required": [
"summary",
"status"
]
}
},
"ActionItemsResponse": {
"type": "object",
"properties": {
"action_items": {
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object"
}
},
"status": {
"type": "string"
}
}
},
"required": [
"action_items",
"status"
]
}
}
},
"examples": {
"VttSubtitlesResponse": {
"value": "WEBVTT\n00:12.340 --> 00:16.220\nLast year I showed these two slides said that demonstrate\n00:16.200 --> 00:20.040\nthat the Arctic ice cap which for most of the last 3,000,000 years has been the\n00:20.020 --> 00:25.040\nsize of the lower 48 States has shrunk by 40% but this understates\n"
},
"SrtSubtitlesResponse": {
"value": "1\n00:00:13,160 --> 00:00:16,694\nLast year I showed these two slides that demonstrate that the Arctic\n\n2\n00:00:16,734 --> 00:00:20,214\nice cap, which for most of the last 3 million years has been the size\n\n3\n00:00:20,254 --> 00:00:23,274\nof the lower 48 states, has shrunk by 40%.\n"
}
},
"responses": {
"BadRequest": {
"x-label": "Bad request",
"description": "Bad request",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Error"
},
"example": {
"error": "This is a sample error message"
}
}
}
},
"Unauthorized": {
"x-label": "Unauthorized",
"description": "Unauthorized",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Error"
},
"example": {
"error": "Authentication error, API token missing/invalid"
}
}
}
},
"CannotAccessUploadedFile": {
"x-label": "Cannot access uploaded file",
"description": "Cannot access uploaded file",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Error"
},
"example": {
"error": "Cannot access uploaded file"
}
}
}
},
"NotFound": {
"x-label": "Not found",
"description": "Not found",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Error"
},
"example": {
"error": "Not found"
}
}
}
},
"TooManyRequests": {
"x-label": "Too many requests",
"description": "Too many requests",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Error"
},
"example": {
"error": "Too Many Requests"
}
}
},
"headers": {
"Retry-After": {
"description": "The number of seconds to wait before retrying the request",
"schema": {
"type": "integer"
}
}
}
},
"InternalServerError": {
"x-label": "Internal server error",
"description": "An error occurred while processing the request",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Error"
},
"example": {
"error": "Internal server error. Please retry your request. If the error persists, please contact support@assemblyai.com for more information."
}
}
}
},
"ServiceUnavailable": {
"x-label": "Service unavailable",
"description": "Service unavailable"
},
"GatewayTimeout": {
"x-label": "Gateway timeout",
"description": "Gateway timeout"
}
},
"securitySchemes": {
"ApiKey": {
"type": "apiKey",
"in": "header",
"name": "Authorization"
}
}
}
}