Own Voice

capability voice · v0.1.0 · scoped read / transcribe / synthesize

Endpoints

POST	/api/v1/stt	transcribe	Transcribe audio (multipart or audio_b64) to text
POST	/api/v1/tts	synthesize	Synthesize text to audio (wav default)
GET	/api/v1/voices	read	List installed voices

v0.1 — Phase 1. The /api/v1/stt and /api/v1/tts endpoints currently return 501. whisper.cpp + Piper engines wire in Phase 2 (see SPEC.md in the repo).