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

### Authentication

API Key authentication via header

### Request

Params to create a transcript

- **audio_url** _string_ **Required** `format: "url"`  
  The URL of the audio or video file to transcribe.

- **speech_models** _list of strings_ **Required**  
  List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. See [Model Selection](/content/docs/pre-recorded-audio/select-the-speech-model/index.html) for available models and routing behavior.

- **audio_end_at** _integer_ **Optional**  
  The point in time, in milliseconds, to stop transcribing in your media file. See [Set the start and end of the transcript](/content/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript/index.html) for more details.

- **audio_start_from** _integer_ **Optional**  
  The point in time, in milliseconds, to begin transcribing in your media file. See [Set the start and end of the transcript](/content/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript/index.html) for more details.

- **auto_highlights** _boolean_ **Optional** Defaults to `false`  
  Enable [Key Phrases](/content/docs/speech-understanding/identify-highlights/index.html), either true or false

- **content_safety** _boolean_ **Optional** Defaults to `false`  
  Enable [Content Moderation](/content/docs/content-moderation/index.html), can be true or false

- **content_safety_confidence** _integer_ **Optional** `25-100` Defaults to `50`  
  The confidence threshold for the [Content Moderation](/content/docs/content-moderation/index.html) model. Values must be between 25 and 100.

- **custom_spelling** _list of objects_ **Optional**  
  Customize how words are spelled and formatted using to and from values. See [Custom Spelling](/content/docs/pre-recorded-audio/correct-spelling-of-terms/index.html) for more details.

- **disfluencies** _boolean_ **Optional** Defaults to `false`  
  Transcribe [Filler Words](/content/docs/pre-recorded-audio/include-filler-words/index.html), like “umm”, in your media file; can be true or false

- **domain** _string or null_ **Optional**  
  Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `"medical-v1"` to enable [Medical Mode](/content/docs/pre-recorded-audio/medical-mode/index.html) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages.

- **entity_detection** _boolean_ **Optional** Defaults to `false`  
  Enable [Entity Detection](/content/docs/speech-understanding/detect-entities-in-transcript/index.html), can be true or false

- **filter_profanity** _boolean_ **Optional** Defaults to `false`  
  Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](/content/docs/profanity-filtering/index.html) for more details.

- **format_text** _boolean_ **Optional** Defaults to `true`  
  Enable [Text Formatting](/content/docs/pre-recorded-audio/index.html), can be true or false

- **iab_categories** _boolean_ **Optional** Defaults to `false`  
  Enable [Topic Detection](/content/docs/speech-understanding/detect-discussion-topics/index.html), can be true or false

- **keyterms_prompt** _list of strings_ **Optional**  
  Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](/content/docs/pre-recorded-audio/keyterms-prompting/index.html) for more details.

- **language_code** _enum or null_ **Optional**  
  The language of your audio file. Possible values are found in [Supported Languages](/content/docs/pre-recorded-audio/supported-languages/index.html). The default value is ‘en_us’.

- **language_detection** _boolean_ **Optional** Defaults to `false`  
  Enable [Automatic language detection](/content/docs/pre-recorded-audio/language-detection/index.html), either true or false.

- **multichannel** _boolean_ **Optional** Defaults to `false`  
  Enable [Multichannel](/content/docs/pre-recorded-audio/transcribe-multiple-audio-channels/index.html) transcription, can be true or false.

- **prompt** _string_ **Optional**  
  Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](/content/docs/pre-recorded-audio/prompting/index.html) for best practices.  
  Note: This parameter is only supported for the Universal-3 Pro model.

- **punctuate** _boolean_ **Optional** Defaults to `true`  
  Enable [Automatic Punctuation](/content/docs/pre-recorded-audio/index.html), can be true or false.

- **redact_pii** _boolean_ **Optional** Defaults to `false`  
  Redact PII from the transcribed text using the Redact PII model, can be true or false. See [PII Redaction](/content/docs/pii-redaction/index.html) for more details.

- **webhook_url** _string_ **Optional** `format: "url"`  
  The URL to which we send [webhook](/content/docs/deployment/webhooks-for-pre-recorded-audio/index.html) requests.

### Response

Transcript created and queued for processing

- **audio_url** _string_ `format: "url"`  
  The URL of the media that was transcribed.

- **auto_highlights** _boolean_  
  Whether [Key Phrases](/content/docs/speech-understanding/identify-highlights/index.html) is enabled, either true or false.

- **id** _string_ `format: "uuid"`  
  The unique identifier of your transcript.

- **language_confidence** _double_ `0-1`  
  The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See [Automatic Language Detection](/content/docs/pre-recorded-audio/language-detection/index.html) for more details.

- **status** _enum_  
  The status of your transcript. Possible values are queued, processing, completed, or error.  
  Allowed values: queued, processing, completed, error.

- **webhook_auth** _boolean_  
  Whether [webhook](/content/docs/deployment/webhooks-for-pre-recorded-audio/index.html) authentication details were provided.