/v1/schemas/assemblyai/audio/v2/transcript?kind=output
Response body
74 properties · 12 required · 34 $defs| property | type | description | constraints |
|---|---|---|---|
| audio_url* | string | The URL of the media that was transcribed | format: url |
| auto_highlights* | boolean | Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) is enabled, either true or false | |
| id* | string | The unique identifier of your transcript | format: uuid |
| language_confidence* | any | 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. | 0 ≤ n ≤ 1 · format: double |
| language_confidence_threshold* | any | The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more d… | 0 ≤ n ≤ 1 · format: float |
| redact_pii* | boolean | Whether [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) is enabled, either true or false | |
| status* | enum | The status of your transcript. Possible values are queued, processing, completed, or error. | queued | processing | completed | error |
| summarization* | boolean | 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 [u… | deprecated |
| webhook_auth* | boolean | Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided | |
| acoustic_model* | string | This parameter does not currently have any functionality attached to it. | deprecated |
| language_model* | string | This parameter does not currently have any functionality attached to it. | deprecated |
| speech_model* | any | 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). | deprecated |
| audio_channels | integer | 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. | |
| audio_duration | any | The duration of this transcript object's media file, in seconds | |
| audio_end_at | any | 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. | |
| audio_start_from | any | 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. | |
| auto_chapters | any | 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. Se… | deprecated |
| auto_highlights_result | AutoHighlightsResult | An array of results for the Key Phrases model, if it is enabled. See [Key phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information. | nullable |
| chapters | any | 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. | |
| confidence | any | The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence) | 0 ≤ n ≤ 1 · format: double |
| content_safety | any | Whether [Content Moderation](https://www.assemblyai.com/docs/content-moderation) is enabled, can be true or false | |
| content_safety_labels | ContentSafetyLabelsResult | An array of results for the Content Moderation model, if it is enabled. See [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information. | nullable |
| custom_spelling | any | 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-term… | |
| disfluencies | any | Whether [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", are transcribed; either true or false. This is the value that was applied to the transcript, which is the value from the request or, when the request d… | |
| domain | any | 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 medication names. When set to `"veterinary-v1"`, [Veterinary Mode]… | |
| entities | any | An array of results for the Entity Detection model, if it is enabled. See [Entity detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) for more information. | |
| entity_detection | any | Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) is enabled, can be true or false | |
| error | string | Error message of why the transcript failed | |
| filter_profanity | any | Whether [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) is enabled, either true or false | |
| format_text | any | Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false | |
| iab_categories | any | Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) is enabled, can be true or false | |
| iab_categories_result | TopicDetectionModelResult | The result of the Topic Detection model, if it is enabled. See [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information. | nullable |
| keyterms_prompt | string[] | Improve accuracy with up to 200 (for Universal-2) or 1000 (for AssemblyAI-STT-3.7) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/prompting#keyterms-prompting) for more… | |
| language_code | enum | string | The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages). | |
| language_codes | any | The language codes of your audio file. Used for [Code switching](https://www.assemblyai.com/docs/pre-recorded-audio/code-switching). On AssemblyAI-STT-3.7, accepts any number of supported languages, and English isn't required. On Universal-2, accepts at most t… | |
| language_detection | any | Whether [Automatic language detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) is enabled, either true or false | |
| language_detection_options | object | Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection). | |
| metadata | object | Additional information about the transcript, including any warnings raised while processing the request. | |
| multichannel | any | 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 | |
| prompt | string | 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. | |
| punctuate | any | Whether [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false | |
| redact_pii_audio | any | Whether a redacted version of the audio file was generated, either true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information. | |
| redact_pii_audio_options | object | The options for PII-redacted audio, if redact_pii_audio is enabled. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more information. | |
| redact_pii_audio_quality | enum | 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. | mp3 | wav · nullable |
| redact_pii_policies | any | The list of PII Redaction policies that were enabled, if PII Redaction is enabled. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more information. | |
| redact_pii_sub | enum | 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. | entity_name | hash |
| redact_pii_return_unredacted | any | 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) f… | |
| sentiment_analysis | any | Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) is enabled, can be true or false | |
| sentiment_analysis_results | any | An array of results for the Sentiment Analysis model, if it is enabled. See [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) for more information. | |
| speaker_labels | any | Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false | |
| speakers_expected | any | 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. | |
| speech_model_used | enum | 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. | assemblyai-stt-3-7 | universal-2 |
| speech_models | any | List of speech models from the request that were considered to transcribe the audio. For new accounts created on or after November 17, 2026, if not specified in the request, this defaults to `["assemblyai-stt-3-7"]`. See [Model Selection](https://www.assemblya… | |
| speech_threshold | any | 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](https://www.assemblyai.com/docs/speech-threshold) for more details. | 0 ≤ n ≤ 1 · format: float |
| speech_understanding | object | 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.assembly… | |
| summary | any | 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 summari… | deprecated |
| summary_model | any | The Summarization model used to generate the summary, 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 fle… | deprecated |
| summary_type | any | 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 th… | deprecated |
| remove_audio_tags | enum | AssemblyAI-STT-3.7 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 AssemblyAI-STT-3.7 model. | all | speaker · nullable |
| temperature | any | 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. | 0 ≤ n ≤ 1 |
| text | any | The textual transcript of your media file | |
| unredacted_text | any | 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. … | |
| throttled | any | True while a request is throttled and false when a request is no longer throttled | |
| utterances | any | When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects. See [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded… | |
| unredacted_utterances | any | 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` fie… | |
| webhook_auth_header_name | any | 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. Requ… | |
| webhook_status_code | any | 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 | |
| webhook_url | any | The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests. | format: url |
| words | any | An array of temporally-sequential word objects, one for each word in the transcript. | |
| unredacted_words | any | 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 rem… | |
| custom_topics | any | This parameter does not currently have any functionality attached to it. | deprecated |
| speed_boost | any | This parameter does not currently have any functionality attached to it. | deprecated |
| topics | string[] | This parameter does not currently have any functionality attached to it. | deprecated |
| translated_texts | object | Translated text keyed by language code. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details. |
Types
34 $defsActionItemsRequestBodyobject
Request body for [Action Items](https://www.assemblyai.com/docs/speech-understanding/action-items).
| action_items* | object |
ActionItemsResponseobject
| action_items | object | ||
| required | any |
AudioIntelligenceModelStatusenum
Either success, or unavailable in the rare case that the model failed
success | unavailable
AutoHighlightResultobject
| count* | integer | The total number of times the key phrase appears in the audio file | |
| rank* | number | The total relevancy to the overall audio file of this key phrase - a greater number means more relevant | 0 ≤ n ≤ 1 · format: float |
| text* | string | The text itself of the key phrase | |
| timestamps* | Timestamp[] | The timestamp of the of the key phrase |
AutoHighlightsResultobject
An array of results for the Key Phrases model, if it is enabled. See [Key phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) for more information.
| status* | enum | The status of the Key Phrases model. Either success, or unavailable in the rare case that the model failed. | success | unavailable |
| results* | AutoHighlightResult[] | A temporally-sequential array of Key Phrases |
Chapterobject
Chapter of the audio file
| gist* | string | An ultra-short summary (just a few words) of the content spoken in the chapter | |
| headline* | string | A single sentence summary of the content spoken during the chapter | |
| summary* | string | A one paragraph summary of the content spoken during the chapter | |
| start* | integer | The starting time, in milliseconds, for the chapter | |
| end* | integer | The starting time, in milliseconds, for the chapter |
ContentSafetyLabelobject
| label* | string | The label of the sensitive topic | |
| confidence* | number | The confidence score for the topic being discussed, from 0 to 1 | 0 ≤ n ≤ 1 · format: double |
| severity* | number | How severely the topic is discussed in the section, from 0 to 1 | 0 ≤ n ≤ 1 · format: double |
ContentSafetyLabelResultobject
| text* | string | The transcript of the section flagged by the Content Moderation model | |
| labels* | ContentSafetyLabel[] | An array of safety labels, one per sensitive topic that was detected in the section | |
| sentences_idx_start* | integer | The sentence index at which the section begins | |
| sentences_idx_end* | integer | The sentence index at which the section ends | |
| timestamp* | Timestamp | Timestamp information for the section |
ContentSafetyLabelsResultobject
An array of results for the Content Moderation model, if it is enabled. See [Content moderation](https://www.assemblyai.com/docs/content-moderation) for more information.
| status* | enum | The status of the Content Moderation model. Either success, or unavailable in the rare case that the model failed. | success | unavailable |
| results* | ContentSafetyLabelResult[] | An array of results for the Content Moderation model | |
| summary* | object | A summary of the Content Moderation confidence results for the entire audio file | |
| severity_score_summary* | object | A summary of the Content Moderation severity results for the entire audio file |
CustomFormattingRequestBodyobject
Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting).
| custom_formatting* | object |
CustomFormattingResponseobject
| custom_formatting | object |
Entityobject
A detected entity
| entity_type* | enum | The type of entity for the detected entity | account_number | banking_information | blood_type | credit_card_cvv | credit_card_expiration | credit_card_number · +41 more |
| text* | string | The text for the detected entity | |
| start* | integer | The starting time, in milliseconds, at which the detected entity appears in the audio file | |
| end* | integer | The ending time, in milliseconds, for the detected entity in the audio file |
EntityTypeenum
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.
account_number | banking_information | blood_type | credit_card_cvv | credit_card_expiration | credit_card_number · +41 more
PiiPolicyenum
The type of PII to redact
account_number | banking_information | blood_type | credit_card_cvv | credit_card_expiration | credit_card_number · +48 more
RedactPiiAudioQualityenum
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.
mp3 | wav
Sentimentenum
POSITIVE | NEUTRAL | NEGATIVE
SentimentAnalysisResultobject
The result of the Sentiment Analysis model
| text* | string | The transcript of the sentence | |
| start* | integer | The starting time, in milliseconds, of the sentence | |
| end* | integer | The ending time, in milliseconds, of the sentence | |
| sentiment* | enum | The detected sentiment for the sentence, one of POSITIVE, NEUTRAL, NEGATIVE | POSITIVE | NEUTRAL | NEGATIVE |
| confidence* | number | The confidence score for the detected sentiment of the sentence, from 0 to 1 | 0 ≤ n ≤ 1 · format: double |
| channel | any | The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially. | |
| speaker* | any | The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null |
SeverityScoreSummaryobject
| low* | number | 0 ≤ n ≤ 1 · format: double | |
| medium* | number | 0 ≤ n ≤ 1 · format: double | |
| high* | number | 0 ≤ n ≤ 1 · format: double |
SpeakerIdentificationRequestBodyobject
Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification).
| speaker_identification* | object |
SpeakerIdentificationResponseobject
| speaker_identification | object |
SpeechModelenum
assemblyai-stt-3-7 | universal-2
SubstitutionPolicyenum
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.
entity_name | hash
SummarizationRequestBodyobject
Request body for [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization).
| summariazation | object |
SummarizationResponseobject
| summarization | object | ||
| required | any |
Timestampobject
Timestamp containing a start and end property in milliseconds
| start* | integer | The start time in milliseconds | |
| end* | integer | The end time in milliseconds |
TopicDetectionModelResultobject
The result of the Topic Detection model, if it is enabled. See [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) for more information.
| status* | enum | The status of the Topic Detection model. Either success, or unavailable in the rare case that the model failed. | success | unavailable |
| results* | TopicDetectionResult[] | An array of results for the Topic Detection model | |
| summary* | object | The overall relevance of topic to the entire audio file |
TopicDetectionResultobject
The result of the topic detection model
| text* | string | The text in the transcript in which a detected topic occurs | |
| labels | object[] | An array of detected topics in the text | |
| timestamp | Timestamp | Timestamp containing a start and end property in milliseconds |
TranscriptCustomSpellingobject
Object containing words or phrases to replace, and the word or phrase to replace with
| from* | string[] | Words or phrases to replace | |
| to* | string | Word to replace with |
TranscriptLanguageCodeenum
The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).
en | en_au | en_uk | en_us | es | fr · +99 more
TranscriptStatusenum
The status of your transcript. Possible values are queued, processing, completed, or error.
queued | processing | completed | error
TranscriptUtteranceobject
| confidence* | number | The confidence score for the transcript of this utterance | 0 ≤ n ≤ 1 · format: double |
| start* | integer | The starting time, in milliseconds, of the utterance in the audio file | |
| end* | integer | The ending time, in milliseconds, of the utterance in the audio file | |
| text* | string | The text for this utterance | |
| words* | TranscriptWord[] | The words in the utterance. | |
| channel | any | The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially. | |
| speaker* | string | 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. | |
| speaker_confidence | any | The confidence score for the speaker label of this utterance, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`. | 0 ≤ n ≤ 1 · format: double |
| translated_texts | object | Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "Übersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation. |
TranscriptWordobject
| confidence* | number | The confidence score for the transcript of this word | 0 ≤ n ≤ 1 · format: double |
| start* | integer | The starting time, in milliseconds, for the word | |
| end* | integer | The ending time, in milliseconds, for the word | |
| text* | string | The text of the word | |
| channel | any | The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially. | |
| speaker* | any | The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null | |
| speaker_confidence | any | The confidence score for the speaker label of this word, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`. | 0 ≤ n ≤ 1 · format: double |
TranslationRequestBodyobject
Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation).
| translation* | object |
TranslationResponseobject
| translation | object |
Validate a payload
before you spend tokens$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"assemblyai","endpointId":"v2/transcript","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}