MOSS-TTS Technical Report
This work addresses the need for efficient and controllable text-to-speech systems, though it appears incremental as it builds on existing tokenization and transformer methods.
The authors tackled the problem of scalable speech generation by introducing MOSS-TTS, a foundation model using discrete audio tokens and autoregressive modeling, which supports zero-shot voice cloning, token-level duration control, and stable long-form generation across multilingual settings.
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.