メインコンテンツへスキップ
更新日: 2026-06-06

Speech-to-Text (STT)

Transcribe audio files to text, compatible with the OpenAI Whisper API format.

Request Parameters

Supported Audio Formats

mp3, mp4, mpeg, mpga, m4a, wav, webm

Request Examples

Response Examples

JSON Format

verbose_json Format

SRT Format


Audio Translation

Translate non-English audio to English text. Parameters are the same as the transcription endpoint.
Python
Specifying the language parameter can improve transcription accuracy. Audio file size limit is 25MB.