Submit a transcript
api.assemblyai.com with api.eu.assemblyai.com.Authorizations
Body
Params to create a transcript
The parameters for creating a transcript
The URL of the audio or video file to transcribe.
The point in time, in milliseconds, to stop transcribing in your media file. See Set the start and end of the transcript for more details.
The point in time, in milliseconds, to begin transcribing in your media file. See Set the start and end of the transcript for more details.
Enable Auto Chapters, can be true or false. Requires punctuate to be true, and cannot be enabled together with summarization. Deprecated - use LLM Gateway instead for more flexible chapter summaries. See the updated Auto Chapters page for details.
Note: This parameter is only supported for the Universal-2 model.
Enable Key Phrases, either true or false
Enable Content Moderation, can be true or false
The confidence threshold for the Content Moderation model. Values must be between 25 and 100. Requires content_safety to be enabled; otherwise it's ignored.
25 <= x <= 100Customize 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 for more details.
Transcribe Filler Words, like "umm", in your media file; can be true or false. Supported on Universal-3.5 Pro and Universal-2.
Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to "medical-v1" to enable Medical Mode for improved accuracy of medical terms such as medications, procedures, conditions, and dosages.
Supported 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.
medical-v1, null Enable Entity Detection, can be true or false
Filter profanity from the transcribed text, can be true or false. See Profanity Filtering for more details.
Enable Text Formatting, can be true or false
Enable Topic Detection, can be true or false
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 for more details.
The language of your audio file. Possible values are found in Supported Languages.
If you don't specify a language, it's detected automatically. Cannot be used together with language_detection.
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 The language codes of your audio file. Used for Code switching
One of the values specified must be en.
The language of your audio file. Possible values are found in Supported Languages.
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 The confidence threshold for the automatically detected language.
An error will be returned if the language confidence is below this threshold.
Defaults to 0. Can only be set when language_detection is enabled. See Automatic Language Detection for more details.
0 <= x <= 1Automatic 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.
Specify options for Automatic Language Detection.
Enable Multichannel transcription, can be true or false.
Provide natural language prompting of up to 1,500 words of contextual information to the model. See the Prompting Guide for best practices.
Note: This parameter is only supported for the Universal-3.5 Pro model.
Enable Automatic Punctuation, can be true or false
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 for more details.
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 for more details.
Specify options for PII redacted audio files.
Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details.
mp3, wav "mp3"
The list of PII Redaction policies to enable. See PII redaction for more details.
The type of PII to redact
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 The replacement logic for detected PII, can be entity_name or hash. See PII redaction for more details.
entity_name, hash 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.
When 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 for more details.
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.
This is a literal find-and-replace (tolerant of casing, surrounding punctuation, and minor spacing/hyphenation), not a model — 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 for more details.
Enable Sentiment Analysis, can be true or false. Requires punctuate to be true.
Enable Speaker diarization, can be true or false. Requires punctuate to be true.
Specify options for Speaker diarization. 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.
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 for more details.
Optional. Supported values: universal-3-5-pro, universal-2. If omitted, defaults to ["universal-3-5-pro", "universal-2"]. See Model Selection for available models and routing behavior.
The speech model to use for the transcription. See Model Selection for available models.
universal-3-5-pro, universal-2 Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive. See Speech Threshold for more details.
0 <= x <= 1Enable speech understanding tasks like Translation, Speaker Identification, and Custom Formatting. See the task-specific docs for available options and configuration.
Enable 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 instead for more flexible summaries. See the updated Summarization page for details.
Note: This parameter is only supported for the Universal-2 model.
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 instead for more flexible summaries. See the updated Summarization page for details.
informative, conversational, catchy 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 instead for more flexible summaries. See the updated Summarization page for details.
bullets, bullets_verbose, gist, headline, paragraph 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.
Note: This parameter is only supported for the Universal-3.5 Pro model.
all, speaker Control the amount of randomness injected into the model's response. See the Prompting Guide for more details.
Note: This parameter only takes effect on the Universal-3.5 Pro model.
0 <= x <= 1This parameter does not currently have any functionality attached to it.
This parameter does not currently have any functionality attached to it.
Callbacks
POST{$request.body#/webhook_url}transcriptReadyWebhook
Body
Response
Successfully received the notification
POST{$request.body#/webhook_url}redactedAudioWebhook
Response
Transcript created and queued for processing
A transcript object
The URL of the media that was transcribed
Whether Key Phrases is enabled, either true or false
The unique identifier of your transcript
The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See Automatic Language Detection for more details.
0 <= x <= 1The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. See Automatic Language Detection for more details.
0 <= x <= 1Whether PII Redaction is enabled, either true or false
The status of your transcript. Possible values are queued, processing, completed, or error.
queued, processing, completed, error Whether Summarization is enabled, either true or false. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.
Note: This parameter is only supported for the Universal-2 model.
This parameter does not currently have any functionality attached to it.
This parameter does not currently have any functionality attached to it.
The number of audio channels in the audio file. This is only present when multichannel is enabled.
The duration of this transcript object's media file, in seconds
The point in time, in milliseconds, in the file at which the transcription was terminated. See Set the start and end of the transcript for more details.
The point in time, in milliseconds, in the file at which the transcription was started. See Set the start and end of the transcript for more details.
Whether Auto Chapters is enabled, can be true or false. Deprecated - use LLM Gateway instead for more flexible chapter summaries. See the updated Auto Chapters page for details.
Note: This parameter is only supported for the Universal-2 model.
An array of results for the Key Phrases model, if it is enabled. See Key Phrases for more information.
An array of temporally sequential chapters for the audio file. See Auto Chapters for more information.
The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)
0 <= x <= 1Whether Content Moderation is enabled, can be true or false
An array of results for the Content Moderation model, if it is enabled. See Content moderation for more information.
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 for more details.
Transcribe Filler Words, like "umm", in your media file; can be true or false. Supported on Universal-3.5 Pro and Universal-2.
The domain-specific model applied to the transcript. When set to "medical-v1", Medical Mode was used to improve accuracy for medical terminology.
An array of results for the Entity Detection model, if it is enabled. See Entity detection for more information.
Whether Entity Detection is enabled, can be true or false
Error message of why the transcript failed
Whether Profanity Filtering is enabled, either true or false
Whether Text Formatting is enabled, either true or false
Whether Topic Detection is enabled, can be true or false
The result of the Topic Detection model, if it is enabled. See Topic Detection for more information.
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 for more details.
The language of your audio file. Possible values are found in Supported Languages.
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 The language codes of your audio file. Used for Code switching
One of the values specified must be en.
The language of your audio file. Possible values are found in Supported Languages.
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 Whether Automatic language detection is enabled, either true or false
Specify options for Automatic Language Detection.
Whether Multichannel transcription was enabled in the transcription request, either true or false
Provide natural language prompting of up to 1,500 words of contextual information to the model. See the Prompting Guide for best practices.
Note: This parameter is only supported for the Universal-3.5 Pro model.
Whether Automatic Punctuation is enabled, either true or false
Whether a redacted version of the audio file was generated, either true or false. See PII redaction for more information.
The options for PII-redacted audio, if redact_pii_audio is enabled. See PII redaction for more information.
The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled. See PII redaction for more information.
mp3, wav "mp3"
The list of PII Redaction policies that were enabled, if PII Redaction is enabled. See PII redaction for more information.
The type of PII to redact
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 The replacement logic for detected PII, can be entity_name or hash. See PII redaction for more details.
entity_name, hash 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 for more information.
Whether Sentiment Analysis is enabled, can be true or false
An array of results for the Sentiment Analysis model, if it is enabled. See Sentiment Analysis for more information.
Whether Speaker diarization is enabled, can be true or false
Tell the speaker label model how many speakers it should attempt to identify. See Set number of speakers expected for more details.
The speech model that was actually used for the transcription. See Model Selection for available models.
universal-3-5-pro, universal-2 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 for available models and routing behavior.
The speech model to use for the transcription. See Model Selection for available models.
universal-3-5-pro, universal-2 Defaults to null. Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive. See Speech Threshold for more details.
0 <= x <= 1Speech understanding tasks like Translation, Speaker Identification, and Custom Formatting. See the task-specific docs for available options and configuration.
The generated summary of the media file, if Summarization is enabled. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.
The Summarization model used to generate the summary, if Summarization is enabled. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.
The type of summary generated, if Summarization is enabled. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.
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.
Note: This parameter is only supported for the Universal-3.5 Pro model.
all, speaker The temperature that was used for the model's response. See the Prompting Guide for more details.
Note: This parameter only takes effect on the Universal-3.5 Pro model.
0 <= x <= 1The textual transcript of your media file
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 for more information.
True while a request is throttled and false when a request is no longer throttled
When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects. See Speaker diarization and Multichannel transcription for more information.
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 for more information.
An array of temporally-sequential word objects, one for each word in the transcript.
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 for more information.
This parameter does not currently have any functionality attached to it.
This parameter does not currently have any functionality attached to it.
This parameter does not currently have any functionality attached to it.
Translated text keyed by language code. See Translation for more details.