Speech-to-Text (STT)

Upload an audio file to /v1/audio/transcriptions as multipart/form-data:

cURL
Python (openai)
Node.js (openai)
curl https://api-model.shuntianchuang.cn/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-token" \
  -F file=@audio.mp3 \
  -F model=<model-name>
NOTE

As of 2026-08-24, no speech-recognition (STT) model is listed on the Model Plaza yet; this endpoint becomes usable once such a model goes live. Available models are subject to the real-time list on the Model Plaza.