github diodiogod/TTS-Audio-Suite v4.0.0
🏗️ TTS Audio Suite v4.0.0 - Universal Multi-Engine Architecture

latest releases: v4.27.0, v4.25.1, v4.22.0...
9 months ago

🚨 BREAKING CHANGES

Complete architectural transformation to unified multi-engine TTS system. Workflow migration required - existing workflows are incompatible with v4.0.0.

🚀 NEW UNIFIED ARCHITECTURE

  • Universal TTS nodes work with any engine (TTS Text, TTS SRT, Voice Changer)
  • Engine configuration nodes for seamless switching between ChatterBox, F5-TTS
  • Modular engine adapter system for easy future engine integration
  • Character Voices node provides NARRATOR_VOICE outputs for any engine

⚡ PERFORMANCE OPTIMIZATIONS

  • Cache-aware model loading prevents unnecessary model reloads
  • Smart language grouping processes SRT files by language to reduce model switching
  • Optimized memory usage through intelligent model lifecycle management

🏗️ TECHNICAL FOUNDATIONS

  • Engine adapter pattern enables easy addition of new TTS engines (RVC, Tortoise, etc.)
  • Unified caching system with engine-specific cache management
  • Future-proof architecture supporting any TTS engine while maintaining consistent UX

📁 PROJECT RESTRUCTURE

  • Engine implementations in engines/chatterbox/ and engines/f5tts/
  • Unified interface nodes in nodes/unified/
  • Engine adapters in engines/adapters/
  • Comprehensive utility systems in utils/

🔄 MIGRATION NOTES

  • Complete workflow migration required - old workflows are incompatible with v4
  • This is a new project (TTS Audio Suite) separate from the original ChatterBox project
  • Users must recreate workflows using new unified node structure

This release transforms the project from a ChatterBox extension to a universal multi-engine TTS platform, providing the foundation for supporting any TTS engine while maintaining the same user experience.

Don't miss a new TTS-Audio-Suite release

NewReleases is sending notifications on new releases.