diodiogod/TTS-Audio-Suite v4.5.0

TTS Audio Suite v4.5.0 - Higgs Audio 2 Voice Cloning Integration

on GitHub

🎙️ Higgs Audio 2 Voice Cloning Integration

🌟 What's New

🎙️ Higgs Audio 2 Voice Cloning Engine

• State-of-the-art voice cloning from 30+ second reference audio samples
• Multi-speaker conversations with seamless character switching
• Universal integration with existing TTS Text and TTS SRT nodes
• Multi-language support - English (tested), potential support for Chinese, Korean, German, Spanish

🧠 Smart Audio Processing

• Intelligent chunk combination with automatic boundary detection
• Enhanced audio quality through smart text structure analysis
• Real-time progress tracking for long operations

🏗️ Architecture Improvements

• Modular processor architecture - consistent across all TTS engines
• Centralized cache management with improved performance
• Simplified maintenance with clean code separation

🚀 Quick Start

1. Add Higgs Audio Engine node
2. Connect to TTS Text or TTS SRT node
3. Upload reference audio (30+ seconds)
4. Generate high-quality cloned speech

📥 Installation

Via ComfyUI Manager or:

cd ComfyUI/custom_nodes
git clone https://github.com/diodiogod/TTS-Audio-Suite.git
cd TTS-Audio-Suite
pip install -r requirements.txt

Experience cutting-edge voice cloning! 🎙️✨