MOSSâTTS Family is an openâsource speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for highâfidelity, highâexpressiveness, and complex realâworld scenarios, covering stable longâform speech, multiâspeaker dialogue, voice/character design, environmental sound effects, and realâtime streaming TTS.
OpenMOSS/MOSS-TTS is drawing steady momentum at +3.9 stars/day (54th percentile in the tracked cohort), for a momentum score of 41.3/100. Forks are climbing too, at +0.1/day.
Low breakout odds over the next 14 days, led by star velocity (54th pctl). Confidence is high given the available history.
Reconstructed from 229 snapshots â the time-series GitHubâs API doesnât expose.
~11 forks/day, 11.2Ă the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/OpenMOSS/MOSS-TTS)Transparent heuristic ¡ logged for model training
Percentile rank within the tracked cohort. The score self-calibrates â it answers âaccelerating vs. everything else,â not raw size.