MOSS-TTS Technical Report

Yitian Gong; Botian Jiang; Yiwei Zhao; Yucheng Yuan; Kuangwei Chen; Yaozhou Jiang; Cheng Chang; Dong Hong

cs.SDMar 18, 2026

MOSS-TTS Technical Report

Authors: Yitian Gong, Botian Jiang, Yiwei Zhao, Yucheng Yuan, Kuangwei Chen, Yaozhou Jiang, Cheng Chang, Dong Hong,

Abstract

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

TTS Synthesis

Text-to-speech synthesis converts written language into intelligible, natural-sounding speech with control over voice, prosody, style, and timing.

See all 275 papers

dots.tts Technical Report
Jun 5, 2026Shi Lian, Changtao Li, Bohan Li +6TTS Synthesis Speech Foundation Models
Voxtral TTS
Mar 26, 2026Mistral-AI, :, Alexander H. Liu +186Multilingual TTS Synthesis TTS Synthesis
Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech
Oct 14, 2026Jeseung Lim, Jiseong Woo, Heeseung KimLong-Form TTS Synthesis TTS Synthesis
Department of Physics, University of Seoul, Seoul, Republic of Korea · Department of AI, University of Seoul, Seoul, Republic of Korea

Jun 5, 2026J/K move · Enter open · S save

dots.tts Technical Report

Shi Lian, Changtao Li, Bohan Li, Hankun Wang+5

TTS Synthesis Speech Foundation Models Multilingual TTS Synthesis Text-to-Speech

Open paper AskPDF arXiv

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.

Abstract

TTS Synthesis

Explore similar work

dots.tts Technical Report

Voxtral TTS

Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech