ChatTTS
ChatTTS is a text-to-speech model designed specifically for dialogue scenarios such as LLM assistant, supporting both English and Chinese languages. It is trained with over 100,000 hours of data and offers conversational TTS with fine-grained control over prosodic features like laughter, pauses, and interjections.
What is ChatTTS?
What is ChatTTS? ChatTTS is a generative speech model that enables natural and expressive speech synthesis for daily dialogue, solving the problem of creating interactive and conversational AI assistants.
ChatTTS Use Case?
Use cases for ChatTTS include, but are not limited to, enhancing the natural interaction of AI assistants, creating interactive voice responses for customer service, and improving the dialogue capabilities of smart home devices.
Applicable people for ChatTTS?
The audience for ChatTTS includes developers, researchers, and companies working on AI assistants, voice-enabled technologies, and conversational interfaces.
ChatTTS is free?
The open-source version of ChatTTS on HuggingFace is available for free, but it is a 40,000 hours pre-trained model without SFT.