Skip to main content
POST
Audio Transcriptions

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

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.

model
string
required

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

language
string | null

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

prompt
string | null

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

response_format
string | null

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

timestamp_granularities
string[] | null

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

temperature
number | null

Sampling temperature between 0 and 1.

Required range: 0 <= x <= 1
user
string | null

End-user identifier for abuse tracking.

file_id
string | null

Id of a file previously uploaded to Eden AI.

file_url
string | null

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

Response

200 - application/json

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.

cost
number | null
provider
string | null
text
string | null
usage
Usage · object | null