Skip to main content
POST
Transcribe an audio file

Authorizations

Authorization
string
header
required

API key passed as an Authorization Bearer token: Authorization: Bearer YOUR_API_KEY

Body

multipart/form-data
file
file
required

FLAC, MP3/MPEG/MPGA, MP4/M4A, OGG, WAV, or WebM audio up to 25 MB.

model
string
required

Must be in the environment's transcription allowlist. Requesting a model outside it returns 400 without dispatching audio.

Example:

"openai/whisper-large-v3"

language
string

Optional ISO language code.

Maximum string length: 32
response_format
enum<string>
default:json
Available options:
json,
verbose_json
temperature
number
Required range: 0 <= x <= 1
timestamp_granularities[]
enum<string>[]

Available only with verbose_json; repeat the multipart field for multiple values.

Available options:
word,
segment

Response

OpenAI-compatible JSON transcription response

text
string
required
language
string
duration
number
segments
object[]
words
object[]
usage
object
Last modified on July 27, 2026