Create transcription (speech-to-text)

Authorization

string

header

required

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

multipart/form-data

file

required

Audio file to transcribe

model

string

required

Model ID

language

string

Input language (ISO-639-1)

prompt

string

Optional text to guide the model

response_format

string

json, text, srt, verbose_json, or vtt

temperature

number

Sampling temperature (0-1)

timestamp_granularities[]

string[]

Timestamp granularities to populate: word and/or segment

Transcription in the requested response_format: a JSON object for json/verbose_json, or a text/plain body for text/srt/vtt

The response is of type object.