Create transcription (speech-to-text)

POST

{base_url}

audio

transcriptions

Error

A valid request URL is required to generate request examples

{}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

Authorizations

Authorization

string

header

required

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

Body

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

stream

boolean

Relay the transcript as server-sent events while the provider produces it

Response

Transcription in the requested response_format: a JSON object for json/verbose_json, a text/plain body for text/srt/vtt, or a text/event-stream when stream=true

The response is of type object.

Last modified on September 23, 2026

⌘I

Error

A valid request URL is required to generate request examples

{}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "type": "provider_error",
    "provider": "<string>"
  }
}

admin

system

mcp

passthrough

audio

auth

batch

chat

conversations

embeddings

files

images

messages

models

realtime

responses

usage

health

Create transcription (speech-to-text)

Authorizations

Body

Response