MOSS-TTS Technical Report
/ Authors
Y. Gong, Botian Jiang, Yiwei Zhao, Yucheng Yuan, Kuan-Yu Chen, Yao Jiang, Cheng Chang, Dongwoo Hong, Mingshu Chen, Ruixiao Li
and 16 more authors
Yiyan Zhang, Yang Gao, Hanfu Chen, Ke Chen, Songlin Wang, Xiaogui Yang, Yuqian Zhang, Kexin Huang, Zheng Lin, Kangrui Yu, Zi-jian Chen, Jin Wang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu
/ 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.