Fish Audio S2 Technical Report

Shijia Liao, Yuxuan Wang, Songting Liu, Yifan Cheng, Ruoyi Zhang +9 more
3/9/2026
cs.SDcs.AIcs.CL

Abstract

We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-language descriptions. To scale training, we develop a multi-stage training recipe together with a staged data pipeline covering video captioning and speech captioning, voice-quality assessment, and reward modeling. To push the frontier of open-source TTS, we release our model weights, fine-tuning code, and an SGLang-based inference engine. The inference engine is production-ready for streaming, achieving an RTF of 0.195 and a time-to-first-audio below 100 ms.Our code and weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/s2-pro). We highly encourage readers to visit https://fish.audio to try custom voices.

View on arXivView PDF

Code Implementations(1)

fishaudio/fish-speechOfficial100%

SOTA Open Source TTS

30,0022,535CSS, HTMLOct 10, 20231 months agoNOASSERTION
llamatransformerttsvallevits+2 more

Cite this paper

@article{liao2026fish,
  title  = {Fish Audio S2 Technical Report},
  author = {Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han},
  year   = {2026},
  eprint = {2603.08823},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.08823v2}
}

Discussion