MOSS TTS Nano
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation
FreeOpen source
What you get
MOSS TTS Nano is a free, open-source AI tool published on GitHub by OpenMOSS.
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation
GitHub stars: 4,533
License: Apache-2.0 (free to use)
Language: Python
Topics: audio-tokenizer, chinese, cpu-inference, english, multi-modality, multilingual, onnx, realtime
Last updated: 2026-09-06
How to get it: open the repository on GitHub, read the README and follow the setup steps. HEEEXY lists it in the Lab because it is popular, actively maintained and openly licensed.
More for voice & audio ai
- GPT SoVITS: 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- OpenBMB VoxCPM: VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
- Leon AI Leon: Leon is your open-source personal assistant.