| title | dots.tts Technical Report |
|---|---|
| authors | Shi Lian, Changtao Li, Bohan Li, Hankun Wang, Da Zheng, Junfeng Tian, Yufeng Ma, Colin Zhang, Kai Yu |
| date | 2026-06-05 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.07080 |
| upvotes | 16 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning in the flow-matching head to preserve long-range consistency and reduce drift during generation. Third, we apply reward-free self-corrective post-training to the flow-matching head to further improve robustness and acoustic quality. After being trained on a large-scale multilingual corpus, dots.tts achieves the best average performance on Seed-TTS-Eval, with WERs of 0.94%/1.30%/6.60% and SIM scores of 81.0/77.1/79.5 on the zh/en/zh-hard test sets, respectively. Across other benchmarks, dots.tts also consistently demonstrates open-source state-of-the-art performance, exhibiting strong generation stability, voice cloning ability, and emotional expressiveness. For efficient inference, we further apply CFG-aware MeanFlow distillation, enabling low-latency speech generation with first-packet latencies of 85/54 ms in output streaming and dual-streaming modes, respectively. To facilitate reproducible research and practical deployment, we release the training and inference code, together with the pretrained, post-trained, and MeanFlow-distilled checkpoints, under the Apache 2.0 license. |
cite
@misc{lian2026dots,
title={dots.tts Technical Report},
author={Shi Lian and Changtao Li and Bohan Li and Hankun Wang and Da Zheng and Junfeng Tian and Yufeng Ma and Colin Zhang and Kai Yu},
year={2026},
eprint={2606.07080},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.07080}
}