JoyTTS: LLM-based Spoken Chatbot With Voice Cloning

JoyTTS is an end-to-end spoken chatbot that combines large language models (LLM) with text-to-speech (TTS) technology, featuring voice cloning capabilities. This project is built upon the open-source MiniCPM-o and CosyVoice2 models and trained on 2000 hours of conversational data. We have also provided the complete training code to facilitate further development and optimization by the community. On the testing machine seed-tts-zh, it achieves a SS (speaker similarity) score of 0.73 and a WER (Word Error Rate) of 5.09. The code and models, along with training and inference scripts, are available atthis https URL.

@article{zhou2025_2507.02380,
  title={ JoyTTS: LLM-based Spoken Chatbot With Voice Cloning },
  author={ Fangru Zhou and Jun Zhao and Guoxin Wang },
  journal={arXiv preprint arXiv:2507.02380},
  year={ 2025 }
}