v4.25.1 - Integrated RVC Model Training

TTS Audio Suite v4.25.1

This release adds integrated RVC model training to TTS Audio Suite.

You can now prepare datasets, train RVC models, monitor progress in a live dashboard, and load the resulting models back into the normal RVC voice conversion workflow without leaving the suite.

New

• Integrated RVC model training inside TTS Audio Suite
• New 📦 RVC Dataset Prep node
• New 🎛️ RVC Training Config node
• New unified 🎓 Model Training node
• New live training dashboard with progress, ETA, speed, and recent loss graph
• Support for resume from real checkpoints
• Support for continue_from using prior training artifacts or an existing 🎭 Load RVC Character Model
• Safer interrupt handling with resumable checkpoint saving
• Improved RVC model loading and index auto-detection
• New RVC training workflow example
• Updated README, model layout docs, and engine capability tables

Notes

• resume continues the same training job from saved checkpoints
• continue_from starts a new run from an already trained model or prior training artifacts
• RVC is the first engine with integrated training support in the suite
• The training architecture is unified so future engines can plug into the same workflow later

Included workflow

• RVC 🎓 Model Training

Restart ComfyUI after updating.