Audio Transcriptions
OpenAI-compatible speech-to-text endpoint.
Accepts either multipart/form-data (OpenAI SDK shape: a file upload
plus text fields) or application/json (file_id / file_url plus
text fields). Content-Type drives dispatch.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
JSON request body, references the audio by file_id or file_url.
Exactly one of file_id (an Eden upload id) or file_url (an https URL
or a data:audio/...;base64,... URL) must be set.
provider/model, e.g. 'openai/whisper-1'
ISO-639-1 language code of the input audio (e.g. 'en'). Omit to let the provider auto-detect where supported.
Optional text to guide the model's style or continue a prior audio segment's context.
Transcript format: 'json', 'text', 'srt', 'verbose_json', or 'vtt'. Provider support varies; forwarded as-is.
Timestamp granularities to populate with 'verbose_json' (['word'] and/or ['segment']).
Sampling temperature between 0 and 1.
0 <= x <= 1End-user identifier for abuse tracking.
Id of a file previously uploaded to Eden AI.
An https URL or a base64 data URL pointing at the audio.
Response
Successful Response
OpenAI-compatible transcription response, plus Eden cost / provider.
The provider's full transcript payload passes through — text plus any
language, duration, words, and segments the provider returns
— alongside the Eden-added cost and provider fields.