Transcribe audio

POST
/v2/transcript
Create a transcript from a media file that is accessible via a URL.

Request

This endpoint expects an object.
audio_urlstringRequired
The URL of the audio or video file to transcribe.
audio_end_atintegerOptional
The point in time, in milliseconds, to stop transcribing in your media file
audio_start_fromintegerOptional
The point in time, in milliseconds, to begin transcribing in your media file
auto_chaptersbooleanOptional

Enable Auto Chapters, can be true or false

auto_highlightsbooleanOptional
Enable Key Phrases, either true or false
boost_paramenumOptional
Allowed values: lowdefaulthigh
How much to boost specified words
content_safetybooleanOptional

Enable Content Moderation, can be true or false

content_safety_confidenceintegerOptionalDefaults to 50
The confidence threshold for the Content Moderation model. Values must be between 25 and 100.
custom_spellinglist of objectsOptional
Customize how words are spelled and formatted using to and from values
custom_topicsbooleanOptional
Enable custom topics, either true or false
disfluenciesbooleanOptional
Transcribe Filler Words, like "umm", in your media file; can be true or false
dual_channelbooleanOptional

Enable Dual Channel transcription, can be true or false.

entity_detectionbooleanOptional

Enable Entity Detection, can be true or false

filter_profanitybooleanOptional
Filter profanity from the transcribed text, can be true or false
format_textbooleanOptional
Enable Text Formatting, can be true or false
iab_categoriesbooleanOptional

Enable Topic Detection, can be true or false

language_codeenumOptional

The language of your audio file. Possible values are found in Supported Languages. The default value is ‘en_us’.

language_confidence_thresholddoubleOptional
The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0.
language_detectionbooleanOptional

Enable Automatic language detection, either true or false.

punctuatebooleanOptional
Enable Automatic Punctuation, can be true or false
redact_piibooleanOptional
Redact PII from the transcribed text using the Redact PII model, can be true or false
redact_pii_audiobooleanOptional

Generate a copy of the original media file with spoken PII “beeped” out, can be true or false. See PII redaction for more details.

redact_pii_audio_quality"mp3" or "wav"Optional
Allowed values: mp3wav

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details.

redact_pii_policieslist of enumsOptional

The list of PII Redaction policies to enable. See PII redaction for more details.

redact_pii_sub"entity_name" or "hash"Optional
Allowed values: entity_namehash

The replacement logic for detected PII, can be “entity_name” or “hash”. See PII redaction for more details.

sentiment_analysisbooleanOptional

Enable Sentiment Analysis, can be true or false

speaker_labelsbooleanOptional

Enable Speaker diarization, can be true or false

speakers_expectedintegerOptional

Tells the speaker label model how many speakers it should attempt to identify, up to 10. See Speaker diarization for more details.

speech_model"best" or "nano"Optional
Allowed values: bestnano
The speech model to use for the transcription.
speech_thresholddoubleOptional
Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.
summarizationbooleanOptional

Enable Summarization, can be true or false

summary_modelenumOptional
Allowed values: informativeconversationalcatchy
The model to summarize the transcript
summary_typeenumOptional
Allowed values: bulletsbullets_verbosegistheadlineparagraph
The type of summary
topicslist of stringsOptional
The list of custom topics
webhook_auth_header_namestringOptional
The header name to be sent with the transcript completed or failed webhook requests
webhook_auth_header_valuestringOptional
The header value to send back with the transcript completed or failed webhook requests for added security
webhook_urlstringOptional

The URL to which we send webhook requests. We sends two different types of webhook requests. One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.

word_boostlist of stringsOptional
The list of custom vocabulary to boost transcription probability for

Response

This endpoint returns an object.
idstring
The unique identifier of your transcript
audio_urlstring
The URL of the media that was transcribed
statusenum
Allowed values: queuedprocessingcompletederror
The status of your transcript. Possible values are queued, processing, completed, or error.
webhook_authboolean
Whether webhook authentication details were provided
auto_highlightsboolean
Whether Key Phrases is enabled, either true or false
redact_piiboolean

Whether PII Redaction is enabled, either true or false

summarizationboolean

Whether Summarization is enabled, either true or false

language_modelstringDeprecated
The language model that was used for the transcript
acoustic_modelstringDeprecated
The acoustic model that was used for the transcript
language_codeenumOptional

The language of your audio file. Possible values are found in Supported Languages. The default value is ‘en_us’.

language_detectionbooleanOptional

Whether Automatic language detection is enabled, either true or false

language_confidence_thresholddoubleOptional
The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold.
language_confidencedoubleOptional
The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence)
speech_model"best" or "nano"Optional
Allowed values: bestnano
The speech model to use for the transcription.
textstringOptional
The textual transcript of your media file
wordslist of objectsOptional

An array of temporally-sequential word objects, one for each word in the transcript. See Speech recognition for more information.

utteranceslist of objectsOptional

When dual_channel or speaker_labels is enabled, a list of turn-by-turn utterance objects. See Speaker diarization for more information.

confidencedoubleOptional
The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)
audio_durationintegerOptional
The duration of this transcript object's media file, in seconds
punctuatebooleanOptional
Whether Automatic Punctuation is enabled, either true or false
format_textbooleanOptional
Whether Text Formatting is enabled, either true or false
disfluenciesbooleanOptional
Transcribe Filler Words, like "umm", in your media file; can be true or false
dual_channelbooleanOptional

Whether Dual channel transcription was enabled in the transcription request, either true or false

webhook_urlstringOptional

The URL to which we send webhook requests. We sends two different types of webhook requests. One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.

webhook_status_codeintegerOptional
The status code we received from your server when delivering the transcript completed or failed webhook request, if a webhook URL was provided
webhook_auth_header_namestringOptional
The header name to be sent with the transcript completed or failed webhook requests
auto_highlights_resultobjectOptional

An array of results for the Key Phrases model, if it is enabled. See Key phrases for more information.

audio_start_fromintegerOptional
The point in time, in milliseconds, in the file at which the transcription was started
audio_end_atintegerOptional
The point in time, in milliseconds, in the file at which the transcription was terminated
word_boostlist of stringsOptional
The list of custom vocabulary to boost transcription probability for
boost_paramstringOptional
The word boost parameter value
filter_profanitybooleanOptional

Whether Profanity Filtering is enabled, either true or false

redact_pii_audiobooleanOptional

Whether a redacted version of the audio file was generated, either true or false. See PII redaction for more information.

redact_pii_audio_quality"mp3" or "wav"Optional
Allowed values: mp3wav

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details.

redact_pii_policieslist of enumsOptional

The list of PII Redaction policies that were enabled, if PII Redaction is enabled. See PII redaction for more information.

redact_pii_sub"entity_name" or "hash"Optional
Allowed values: entity_namehash

The replacement logic for detected PII, can be “entity_type” or “hash”. See PII redaction for more details.

speaker_labelsbooleanOptional

Whether Speaker diarization is enabled, can be true or false

speakers_expectedintegerOptional

Tell the speaker label model how many speakers it should attempt to identify, up to 10. See Speaker diarization for more details.

content_safetybooleanOptional

Whether Content Moderation is enabled, can be true or false

content_safety_labelsobjectOptional

An array of results for the Content Moderation model, if it is enabled. See Content moderation for more information.

iab_categoriesbooleanOptional

Whether Topic Detection is enabled, can be true or false

iab_categories_resultobjectOptional

The result of the Topic Detection model, if it is enabled. See Topic Detection for more information.

custom_spellinglist of objectsOptional
Customize how words are spelled and formatted using to and from values
auto_chaptersbooleanOptional

Whether Auto Chapters is enabled, can be true or false

chapterslist of objectsOptional
An array of temporally sequential chapters for the audio file
summary_typestringOptional

The type of summary generated, if Summarization is enabled

summary_modelstringOptional

The Summarization model used to generate the summary, if Summarization is enabled

summarystringOptional

The generated summary of the media file, if Summarization is enabled

custom_topicsbooleanOptional
Whether custom topics is enabled, either true or false
topicslist of stringsOptional
The list of custom topics provided if custom topics is enabled
sentiment_analysisbooleanOptional

Whether Sentiment Analysis is enabled, can be true or false

sentiment_analysis_resultslist of objectsOptional

An array of results for the Sentiment Analysis model, if it is enabled. See Sentiment Analysis for more information.

entity_detectionbooleanOptional

Whether Entity Detection is enabled, can be true or false

entitieslist of objectsOptional

An array of results for the Entity Detection model, if it is enabled. See Entity detection for more information.

speech_thresholddoubleOptional
Defaults to null. Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.
throttledbooleanOptional
True while a request is throttled and false when a request is no longer throttled
errorstringOptional
Error message of why the transcript failed
speed_boostbooleanOptionalDeprecated
Whether speed boost is enabled