Sign in

v126

latestOpenAPI 3.1.0MITraw.githubusercontent.com2026-08-04957391.2 MB
STT

Create transcription

Transcribes audio into text. Accepts base64-encoded audio input as JSON or an OpenAI-style multipart/form-data file upload, and returns the transcribed text.

post/audio/transcriptions

Request body

languagestring

ISO-639-1 language code (e.g., "en", "ja"). Auto-detected if omitted.

modelstring required

STT model identifier

response_format'json' | 'verbose_json'

Output format. "json" (default) returns { text, usage }. "verbose_json" additionally returns task, language, duration, and segment-level timestamps; only supported by OpenAI-compatible providers.

temperaturenumber double

Sampling temperature for transcription

timestamp_granularitiesSTTTimestampGranularity[]

Timestamp detail levels to include when response_format is "verbose_json". "segment" returns segment-level timestamps; "word" additionally returns word-level timestamps in the words array. Ignored unless response_format is "verbose_json".

Example request

{
  "input_audio": {
    "data": "UklGRiQA...",
    "format": "wav"
  },
  "language": "en",
  "model": "openai/whisper-large-v3"
}

Response

Transcription result

durationnumber double

Duration of the input audio in seconds, present when response_format is verbose_json

languagestring

Detected or forced language, present when response_format is verbose_json

taskstring

The task performed, present when response_format is verbose_json

textstring required

The transcribed text

Example response

{
  "text": "Hello, this is a test of OpenAI speech-to-text transcription.",
  "usage": {
    "cost": 0.000508,
    "input_tokens": 83,
    "output_tokens": 30,
    "seconds": 9.2,
    "total_tokens": 113
  }
}