Load model
POSThttps://api.lucidweights.ai/v1/stt/load_model
Warms a model so the first transcription is not delayed. Optional: models load on demand.
Query parameters
| Field | Type | Default | Description |
|---|---|---|---|
| backend | string | ultra | ultra, fast, or normal |
| model_name | string | large | For fast/normal: tiny, base, small, medium, large-v2, large-v3, large, large-v3-turbo, turbo |
Response
200 with a JSON string, e.g. "Model fast-large-v3 successfully loaded." or "Ultra model is loaded on demand."
Example
curl -X POST "https://api.lucidweights.ai/v1/stt/load_model?backend=fast&model_name=large-v3" \ -H "x-api-key: lw_YOUR_SECRET"
WARNING
An unknown model_name does not raise. With a valid backend it returns 200 and a plain-string body describing the mistake. Check the body, not just the status code. Warming is per worker process; a pod with multiple workers may still be cold on the worker that serves your next request.