Release Notes - Version 0.2.5

Version Tracking: Implemented __init__.py for version control.
Memory Management: Fixed memory-related issues.
Stability: Enhanced stability, especially regarding interruptions.

It's been three weeks since the previous release, so here is a new one.

What's New

AzureTTS Enhancements: Added customizable pitch and rate properties, allowing users to match the voice style of Neuro-sama.
Experimental Mem0 Integration: Introduced support for Mem0 as an experimental feature.
Real-Time Configuration Switching: Users can now switch configurations in real-time via the config_alts directory, enabling dynamic adjustments of Live2D, voice, LLM, and other settings directly from the frontend.
Dynamic Background Switching: Allows users to change the background image in real-time on the frontend.
CoquiTTS Support: Added support for CoquiTTS as an additional TTS option.
Chinese Documentation: Comprehensive documentation is now available in Chinese.
AI-Generated Favicon: Introduced a new favicon (favicon.ico), generated by Adobe Firefly Image 3 (trained exclusively on licensed content).
Experimental Upgrade Script: Added an upgrade script for experimental testing.

No Voice Input Mode: Reinstated support for no voice input mode in CLI mode.
TTS Naming Issues: Resolved TTS naming inconsistencies (#29, #30).
File Encoding: Improved file handling for persona prompt and conf.yaml files to support non-UTF-8 encodings, resolving issues related to GBK encoding.
Bug #31: Addressed issue as detailed in GitHub (#31).

API Key Configuration: Removed the api_keys.py file. Users should now add their AzureTTS API keys directly to conf.yaml.
Default Settings Update: Updated the default LLM to qwen2.5 and modified the default language for some ASR components to auto.

Full Changelog: v0.2.4...v0.2.5