System status
Loading…
| GPU | Workload | Temp | 30 s | Power / limit | 30 s | VRAM | Load |
|---|
Host health
Loading…
LLM test inference
—
WAV transcription and voice job
—
Script API
GET /api/status
POST /api/inference JSON: {"worker":0,"prompt":"..."}
POST /api/stt?worker=0&language=auto body: raw WAV content
GET /api/capabilities
Customer accounting, usage limits, and admin commands are reserved for a later version.