MOSS-TTS

OpenMOSS/MOSS-TTS: Open-Source Speech and Sound Generation Model Family

MOSS-TTS is an open-source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It targets high-fidelity, expressive synthesis across stable long-form speech, multi-speaker dialogue, voice/character design, environmental sound effects, and real-time streaming TTS. The repository has accumulated 2,192 stars with 53 added today, indicating active community interest.