MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving, and lightweight product integration.
Pulse
0
Velocity
Stars
1,112
Tiny, multilingual real-time speech generation model runnable on CPU.
A small, efficient TTS model for diverse languages that runs on CPU.
Generate realistic speech in multiple languages directly on your CPU, no GPU required.
Why Trending
Enables real-time, CPU-based TTS for embedded and local applications.
Target Audience
Developers needing lightweight, on-device speech synthesis.
Similar Projects