Generative AI Text-to-Speech Model
39.2k 2026-05-01
2noise/ChatTTS
A generative speech model optimized for natural, expressive dialogue in LLM assistants, featuring fine-grained prosodic control.
Core Features
Conversational TTS optimized for dialogue scenarios
Fine-grained control over prosodic features (laughter, pauses, interjections)
Superior prosody compared to most open-source TTS models
Supports multiple speakers
Supports English and Chinese languages
Quick Start
pip install --upgrade -r requirements.txtDetailed Introduction
ChatTTS is an advanced text-to-speech model specifically engineered for dynamic dialogue scenarios, such as those involving LLM assistants. It excels in generating natural and expressive speech by offering fine-grained control over prosodic elements like laughter, pauses, and interjections. This project provides a robust algorithmic infrastructure and pre-trained models, surpassing many open-source alternatives in prosody, making it a valuable tool for research and development in conversational AI.