ChatTTS

ChatTTS is a generative speech model specifically designed for daily dialogue scenarios, such as LLM assistants. It offers natural and expressive speech with fine-grained control over prosodic features like laughter, pauses, and interjections.

ChatTTS is currently grouped under Voice / Speech, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Conversational TTS optimized for dialogue-based tasks and Providing voice output for LLM assistants in dialogue scenarios. The listed license is AGPL-3.0, which is useful when adoption constraints matter. It also shows measurable community traction with 39.4k GitHub stars.