Transcription

Convert audio to text with word-level timestamps and speaker diarization.

POST /v1/audio/transcriptions

Try it

Modelaudio source

curl https://relayx.timor419.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $RELAYX_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/paraformer-v2",
  "audio_url": "https://example.com/recording.wav",
  "response_format": "verbose_json"
}'