Sign in

v1

latestOpenAPI 3.1.0MIT2026-07-262861121.0 KB

Transcribe audio (and supported video formats) into text using speech recognition models. Supports multiple languages, diarization (model-dependent), and various formats. Most models return synchronous results; some models (for example Elevenlabs-STT and voice cloning workflows) return asynchronous job IDs.

post/transcribe

Request body

audioUrlstring uri required

URL to audio file to transcribe

model'Whisper-Large-V3' | 'Wizper' | 'Elevenlabs-STT' | 'gpt-4o-mini-transcribe' | 'gpt-4o-mini-transcribe-2025-03-20' | 'gpt-4o-mini-transcribe-2025-12-15' | 'gpt-4o-mini-transcribe-latest' | 'openai-whisper-with-video' | 'qwen-voice-clone' | 'minimax-voice-clone'

The STT model to use for transcription

languagestring

Language code for transcription (ISO 639-1 or ISO 639-3). Use 'auto' for auto-detection

actualDurationstring

Actual audio duration in minutes for accurate billing

diarizeboolean

Enable speaker diarization (Elevenlabs-STT only)

tagAudioEventsboolean

Tag non-speech audio events like [laughter], [applause] (Elevenlabs-STT only)

Example request

{
  "audioUrl": "https://example.com/audio.mp3",
  "language": "en"
}

Response

Synchronous transcription response (Whisper/Wizper models)

transcriptionstring required

The transcribed text

Example response

{
  "transcription": "Hello, this is a test transcription."
}