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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Text-to-Speech | EmergentTTS (eval) | Overall WER10.45 | 40 | |
| Zero-Shot Voice Cloning | Seed-TTS-Eval en (test) | WER (%)1.29 | 16 | |
| Zero-Shot Voice Cloning | Seed-TTS-Eval zh (test) | WER0.94 | 16 | |
| Text-to-Speech | CV3-EN | WER4.05 | 15 | |
| Zero-Shot Voice Cloning | Seed-TTS-Eval Average | WER (%)2.92 | 12 | |
| Zero-Shot Voice Cloning | Seed-TTS-Eval zh-hard (test) | WER6.46 | 12 | |
| Text-to-Speech | CV3-Eval Monolingual (hard-en) | WER4.37 | 7 | |
| Text-to-Speech | CV3-Eval Monolingual zh | WER3.51 | 7 | |
| Text-to-Speech | CV3-Eval Monolingual (hard-zh) | WER (%)9.1 | 7 | |
| Text-to-Speech | CV3-Eval Cross-lingual en → zh | WER10.73 | 5 |