IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

@misc{deng2025indextts2breakthroughemotionally,
      title={IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech},
      author={Wei Deng and Xun Zhou and Yi He and Siyi Zhou and Yiquan Zhou and Jinchao Wang and Jingchen Shu},
      year={2025},
      eprint={2506.21619},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.21619},
}