Speech MCP

  • docs
# Changelog ## Recent Improvements - **Complete PyQt UI Migration**: Replaced the old Tkinter UI with a modern PyQt implementation - **Code Refactoring**: Split UI code into multiple components for better maintainability - **Process Management**: Improved process lifecycle management with automatic recovery - **Voice Persistence**: Added configuration system for saving user preferences - **Enhanced Visualization**: Added dynamic audio visualization with animations - **Expanded Voice Options**: Updated to support 54 different voice models - **Improved Error Handling**: Better recovery from common failure modes ## Previous Updates ### v0.4.0 - Added PyQt UI implementation - Implemented voice persistence - Added configuration system ### v0.3.0 - Added Kokoro TTS integration - Expanded voice options - Improved audio processing ### v0.2.0 - Added faster-whisper integration - Improved speech recognition accuracy - Added silence detection ### v0.1.0 - Initial release - Basic Tkinter UI - Speech recognition and synthesis