Built in Python, DiffSinger is an open-source speech and audio tool maintained by MoonInTheRiver. It has 4.9k GitHub stars and 834 forks, and was last updated in July 2026. Topics include aaai2022, diffusion-model and diffusion-speedup.
“DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code”
— MoonInTheRiver, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 4,878 |
| Forks | 834 |
| Language | Python |
| License | MIT |
| Last updated | |
| Owner | MoonInTheRiver |
| Repository | MoonInTheRiver/DiffSinger |
Tags
aaai2022diffusion-modeldiffusion-speedupmidisinging-synthesissinging-voicesinging-voice-databasesinging-voice-synthesis
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.