What's New
- Qwen3-ASR Beta (#281): Add Qwen3-ASR-0.6B CoreML speech recognition with multilingual support
- PocketTTS GPL Separation (#301): Move PocketTTS to core FluidAudio, now available without GPL dependencies for closed-source apps
- Voice Cloning for PocketTTS (#289): Clone any voice from 1-30 second audio samples using Mimi encoder
Full Changelog: v0.12.0...v0.12.1