MOSS-TTS-Nano is an open-source speech and audio tool written in Python, released under the Apache-2.0 license. It has 4.5k GitHub stars and 561 forks, and was last updated in September 2026. Topics include audio-tokenizer, chinese and cpu-inference.
“A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation”
— OpenMOSS, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 4,507 |
| Forks | 561 |
| Language | Python |
| License | Apache-2.0 |
| Last updated | |
| Owner | OpenMOSS |
| Website | openmoss.ai/MOSS-TTS-Nano-Demo |
| Repository | OpenMOSS/MOSS-TTS-Nano |
Tags
audio-tokenizerchinesecpu-inferenceenglishmulti-modalitymultilingualonnxrealtime
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.