Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

dots.tts Technical Report

About

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.

Shi Lian, Changtao Li, Bohan Li, Hankun Wang, Da Zheng, Junfeng Tian, Yufeng Ma, Colin Zhang, Kai Yu• 2026

Related benchmarks

TaskDatasetResultRank
Text-to-SpeechEmergentTTS (eval)
Overall WER10.45
40
Zero-Shot Voice CloningSeed-TTS-Eval en (test)
WER (%)1.29
16
Zero-Shot Voice CloningSeed-TTS-Eval zh (test)
WER0.94
16
Text-to-SpeechCV3-EN
WER4.05
15
Zero-Shot Voice CloningSeed-TTS-Eval Average
WER (%)2.92
12
Zero-Shot Voice CloningSeed-TTS-Eval zh-hard (test)
WER6.46
12
Text-to-SpeechCV3-Eval Monolingual (hard-en)
WER4.37
7
Text-to-SpeechCV3-Eval Monolingual zh
WER3.51
7
Text-to-SpeechCV3-Eval Monolingual (hard-zh)
WER (%)9.1
7
Text-to-SpeechCV3-Eval Cross-lingual en → zh
WER10.73
5
Showing 10 of 11 rows

Other info

GitHub

Follow for update