Create transcription

The model to use for the transcription.

The URL of the audio file to transcribe (cannot be specified if file_id is specified).

The ID of the uploaded file to transcribe (cannot be specified if audio_url is specified).

Hints for the expected languages in the audio. If language_hints is not specified, the languages will be detected automatically.

Identifies different speakers in the audio and automatically adds speaker tags whenever the speaker changes.

An extra context for the transcription. With the context you can hint how words are spelled and formatted.

The URL to which we send webhook requests. The request will be send a transcript is completed or failed.

The header name to be sent with the transcript completed or failed webhook requests.

The header value to send back with the transcript completed or failed webhook requests for added security.

A string provided by the client to track the uploaded file. It can be an ID, a JSON string, or any other text. This value can be used for reference in future API requests or for internal mapping within the client’s systems. The value does not have to be unique. If not provided, it will remain unspecified.

The unique identifier of the transcription.

The status of your transcript. Possible values are queued, processing, completed or error.

When the transcription was created.

The model to use for the transcription.

The URL of the audio file to transcribe.

The ID of the uploaded file to transcribe.

Name of the file.

Hints for the expected languages in the audio. If language_hints is not specified, the languages will be detected automatically.

Identifies different speakers in the audio and automatically adds speaker tags whenever the speaker changes.

An extra context for the transcription. With the context you can hint how words are spelled and formatted.

The duration of the audio in milliseconds. The duration will only be available when the file is processed.

The error message (e.g. audio download failed, invalid audio file).

The URL to which we send webhook requests. The request will be send a transcript is completed or failed.

The header name to be sent with the transcript completed or failed webhook requests.

The header value to send back with the transcript completed or failed webhook requests for added security. This value will never be returned in its original form. Instead, a masked value will be shown, such as: "webhook_auth_header_value": "******************"

The status code we received from your server when delivering the transcript completed or failed webhook request, if a webhook URL was provided.

A string provided by the client to track the uploaded file. It can be an ID, a JSON string, or any other text. This value can be used for reference in future API requests or for internal mapping within the client’s systems. The value does not have to be unique. If not provided, it will remain unspecified.