ChatTTS
ChatTTS is an open-source text-to-speech (TTS) system built on neural network technology and designed for conversational scenarios, capable of producing natural and fluent speech output. Key features include multilingual synthesis (covering Chinese and English), fine-grained prosody and emotion control, and support for batch text processing. It is applicable to intelligent dialogue assistants, voice broadcasting, and audio content generation, and is available for developer deployment and further development.
Timeline (last 90 days)
Vespera's voice uses the locally run ChatTTS model, requiring no additional token consumption; the singing voice is converted via an RVC model trained on a local GPU.
ChatTTS is a conversational speech synthesis model open-sourced in 2024, optimized specifically for Chinese dialogue scenarios; it can automatically generate paralinguistic features such as pauses, filler words, and laughter, supports local deployment, and requires no cloud API calls during inference.
ChatTTS has limited voice timbre control, mainly producing different voices through random sampling; fixing a character's timbre usually requires reference audio or subsequent fine-tuning.
All Facts (3)
Vespera's voice uses the locally run ChatTTS model, requiring no additional token consumption; the singing voice is converted via an RVC model trained on a local GPU.
50%UnverifiedChatTTS is a conversational speech synthesis model open-sourced in 2024, optimized specifically for Chinese dialogue scenarios; it can automatically generate paralinguistic features such as pauses, filler words, and laughter, supports local deployment, and requires no cloud API calls during inference.
50%UnverifiedChatTTS has limited voice timbre control, mainly producing different voices through random sampling; fixing a character's timbre usually requires reference audio or subsequent fine-tuning.
50%