Speech To Text

Transcribe various audio formats to written text using advanced AI models powered by Replicate, including openai/whisper and turian/insanely-fast-whisper-with-video.
Model strength and output quality may vary. Check model reviews on Replicate.

​
How to use

Navigate to the endpoint /replicate/stt.
curl
curl -X POST http://localhost:9000/api/v1/replicate/stt?model=openai/whisper \
  -H "Authorization: Bearer MY_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -f audio: some-audio-input
For details about the parameters, visit the text to speech reference page.