v0.0.6
Added
-
Added
KokoroTTSServiceprocessor. -
Added noise cancellation with
RNNoiseFilter. -
Simplified the
/pipecatskill instructions.
Changed
- Replaced third-party STT/TTS services (Deepgram, Cartesia) with local models: Faster Whisper for speech-to-text and Kokoro for text-to-speech. No API keys required.