Skip to main content
POST
Speech-to-Text

Authorizations

Authorization
string
header
required

Bearer token issued by your workspace.

Body

multipart/form-data
file
file
required

The audio file to transcribe. Supported formats: wav, mp3, flac, ogg, m4a, webm. Maximum size: 15 MB.

model
string
default:freya-stt

The model to use for transcription.

response_format
enum<string>
default:json

The format of the response. json returns {"text": "..."}. text returns plain text. verbose_json includes language, timing, and word-level data.

Available options:
json,
text,
verbose_json
temperature
number
default:0

Sampling temperature between 0 and 1. Lower values are more deterministic.

Response

Transcription successful.

Standard JSON response (response_format=json)

text
string

The transcribed text.

inference_time_ms
number

Server-side inference time in milliseconds.