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 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 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 for more details.

• auto_highlights boolean Optional Defaults to false
  Enable Key Phrases, either true or false

• content_safety boolean Optional Defaults to false
  Enable Content Moderation, can be true or false

• content_safety_confidence integer Optional 25-100 Defaults to 50
  The confidence threshold for the Content Moderation 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 for more details.

• disfluencies boolean Optional Defaults to false
  Transcribe Filler Words, 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 for improved accuracy of medical terms such as medications, procedures, conditions, and dosages.

• entity_detection boolean Optional Defaults to false
  Enable Entity Detection, 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 for more details.

• format_text boolean Optional Defaults to true
  Enable Text Formatting, can be true or false

• iab_categories boolean Optional Defaults to false
  Enable Topic Detection, 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 for more details.

• language_code enum or null Optional
  The language of your audio file. Possible values are found in Supported Languages. The default value is ‘en_us’.

• language_detection boolean Optional Defaults to false
  Enable Automatic language detection, either true or false.

• multichannel boolean Optional Defaults to false
  Enable Multichannel 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 for best practices.
  Note: This parameter is only supported for the Universal-3 Pro model.

• punctuate boolean Optional Defaults to true
  Enable Automatic Punctuation, 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 for more details.

• webhook_url string Optional format: "url"
  The URL to which we send webhook 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 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 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 authentication details were provided.