Audio

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.

post/v3/audio/transcriptions

Request

Base URL
https://api.edenai.run
Auth
HTTP bearer

Request body

tagsunknown

modelstring required

provider/model, e.g. 'openai/whisper-1'

languagestring nullable

ISO-639-1 language code of the input audio (e.g. 'en'). Omit to let the provider auto-detect where supported.

promptstring nullable

Optional text to guide the model's style or continue a prior audio segment's context.

response_formatstring nullable

Transcript format: 'json', 'text', 'srt', 'verbose_json', or 'vtt'. Provider support varies; forwarded as-is.

timestamp_granularitiesstring[] nullable

Timestamp granularities to populate with 'verbose_json' (['word'] and/or ['segment']).

temperaturenumber nullable

Sampling temperature between 0 and 1.

diarizeboolean nullable

Label who speaks when. Not an OpenAI parameter; forwarded as-is. Mistral (Voxtral) models return a speaker_id per segment and require timestamp_granularities=['segment']; Deepgram models prefix the text with speaker labels. Other providers may reject it.

userstring nullable

End-user identifier for abuse tracking.

file_idstring nullable

Id of a file previously uploaded to Eden AI.

file_urlstring nullable

An https URL or a base64 data URL pointing at the audio.

Example request

{
  "tags": {
    "client": "acme",
    "project": "invoices"
  }
}

Response

Successful Response

costnumber nullable

providerstring nullable

textstring nullable

usageobject nullable

Changes

No recorded changes to this operation across all 1 revision of this API.