| title | Fish Audio Drama 3 Technical Report |
|---|---|
| authors | Dawei Han, Shidong Li, Shijia Liao, Jiahua Liu, Songting Liu, Qingzheng Wang, Yuxuan Wang, Xin Chen, Yifan Cheng, Tianyu Li, Gangin Park, Xuehao Yang, Chang Zeng, Haoyang Zhang, Ruoyi Zhang, Xiangyu Zhang |
| date | 2026-10-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.18010 |
| affiliation | Fish Audio |
| upvotes | 26 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters per token. It clones voices from multiple references, follows natural-language direction, revises a take when the next turn gives a note, voices multi-character scenes, edits existing speech by infilling, and synthesizes long-form and streaming audio. Multi-turn revision, scene dubbing, editing by infilling, and streaming text input are new in Drama 3, all in one model. Drama 3 pairs the hybrid linear-attention backbone with a new codebook multi-token-prediction audio decoder that predicts the acoustic codebooks of each frame in dedicated layers that attend over the entire sequence. The model is trained with a three-stage pre-training recipe, instruction fine-tuning, and large-batch reinforcement learning whose only reward is a single learned model of human preference. Its inference engine decodes a single stream at 271 frames per second on one H200, against 177 for Fish Audio S2, although Drama 3 has more than seven times as many parameters. The model weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/drama-3), and inference is available through SGLang-Omni (https://github.com/sgl-project/sglang-omni). We highly encourage readers to visit https://fish.audio to direct their own performances. |
cite
@misc{han2026fish,
title={Fish Audio Drama 3 Technical Report},
author={Dawei Han and Shidong Li and Shijia Liao and Jiahua Liu and Songting Liu and Qingzheng Wang and Yuxuan Wang and Xin Chen and Yifan Cheng and Tianyu Li and Gangin Park and Xuehao Yang and Chang Zeng and Haoyang Zhang and Ruoyi Zhang and Xiangyu Zhang},
year={2026},
eprint={2610.18010},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.18010}
}