ChatTTS

ChatTTS is a powerful text-to-speech system designed for daily dialogue scenarios, such as LLM assistant. The model supports both English and Chinese languages, with a training set composed of 100,000+ hours of Chinese and English audio. The open-source version available on HuggingFace is a 40,000 hours pre-trained model without Self-Fine-Tuning (SFT).

The model is optimized for dialogue-based tasks and enables natural and expressive speech synthesis, supporting multiple speakers. It offers fine-grained control, including laughter, pauses, and interjections, and better prosody compared to most open-source TTS models. The model provides pre-trained models to support further research and development.