MOSS-TTS is a text-to-speech model hosted on Hugging Face that enables developers to generate speech audio from text input. It is built for integration with the Transformers library and supports local or cloud inference. The model is part of the OpenMOSS initiative focused on open AI tools.
In the Voice, TTS & speech space, MOSS TTS takes a focused approach. It focuses on converting text into natural-sounding speech using open models. MOSS TTS is an open-source project aimed at developers. The project is open source (Apache-2.0). The product ships for the web, the command line, and API.
OpenMOSS-Team builds and maintains MOSS TTS, and the product first shipped in 2026. The project is developed in the open on GitHub with 3.9k stars and 16 commits in the last 90 days.
Latest indexed changes and source events
OpenMOSS-Team/MOSS-TTS verified by the PulseGate indexer
Other apps tracked under the same category.
