- AI Gateway
- Speech to Text
OpenAI speech-to-text — the default model for /v1/audio/transcriptions.
| Model Info | |
|---|---|
| Model ID | whisper-1 |
| Author | OpenAI |
| Task | Speech to Text |
| Endpoint | POST /v1/audio/transcriptions |
Usage
Call the model through the gateway's transcription endpoint — see Audio (Speech & Transcription) for the full guide, and the API reference for every parameter.
curl -X POST "$TRUEMEMORY_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $TOKEN" \
-F "file=@./audio.mp3" \
-F "model=whisper-1"