Simplify local speech models

This commit is contained in:
Mohamed Boudra
2026-05-28 15:38:15 +07:00
parent 0737c5c973
commit 8e4cbf8ca6
23 changed files with 192 additions and 2235 deletions

View File

@@ -171,6 +171,8 @@ Single file, validated with `PersistedConfigSchema`.
All fields are optional with sensible defaults.
Local speech model ids are intentionally narrow: STT uses `parakeet-tdt-0.6b-v2-int8`, TTS uses `kokoro-en-v0_19`, and turn detection uses the bundled Silero VAD model.
---
## 3. Schedule