flâneur

[2603.18090] MOSS-TTS Technical Report

arxiv.org · 7,069 words · saved by 1 readers

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.

OpenMOSS MOSS-TTS Technical Report SII-OpenMOSS Team* Abstract arXiv:2603.18090v2 [cs.SD] 20 Mar 2026 This technical report presents MOSS-TTS, a speech generation foundation model built on a scal- able recipe: discrete audio…

saved by

related reading