Features
Self-hosted text-to-speech synthesis
Zero-shot voice cloning from short audio
Multi-language TTS (17 languages)
Fine-tuning of pre-trained models
Python API for integration
Voice conversion between speakers
Custom dataset training scripts
Model validation and evaluation tools
Cross-platform support (Linux, macOS, Windows)
Privacy-controlled offline deployment
Multilingual text-to-speech in 30 languages
Voice cloning with controllable similarity
Voice design from scratch using text prompts
48kHz high-quality audio output
LoRA training for custom voice adaptation
Diffusion-based speech generation
Emotion and prosody control
Node-based workflow in ComfyUI
Supports multiple speaker references
Tokenizer-free architecture
Model weights in safetensors format
Compatible with ComfyUI visual node editing
Open-source and self-hosted
