Skip to main content
POST
Transcribe audio

Authorizations

Authorization
string
header
required

Session token (snat_…) minted by POST /v1/token. Carries the organization and the end user; safe in a browser.

Body

multipart/form-data
file
file
required

The audio: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav or webm; at most 32 MB.

language
string

ISO 639-1 code of the spoken language, when known. Improves accuracy; omitted, the model detects it.

Example:

"es"

environment
enum<string>

The environment this request is recorded under (default dev).

Available options:
dev,
staging,
prod

Response

The transcript

text
string

The transcript, trimmed; empty when nothing was recognised.

language
string | null

The language the model detected, when it reports one.

duration
number | null

Seconds of audio, when the model reports it.

model
string

The transcription model.

usage
object | null

What the model metered: { type: "duration", seconds } or { type: "tokens", input_tokens, output_tokens, … }.

cost
number

USD charged to the organization for this transcription (0 when the catalogue has no price).

request_id
string

The request this transcription is recorded as; its join key in the requests list.