MoonInTheRiver/DiffSinger

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

49
/ 100
Emerging

This project helps musicians, producers, and content creators generate realistic singing voices from lyrics and musical notation. You provide the lyrics and MIDI-based pitch information, and it outputs a high-quality, synthesized singing voice. This tool is ideal for anyone looking to create vocal tracks without needing a human singer.

4,746 stars. No commits in the last 6 months.

Use this if you need to create synthetic singing voice tracks for music, demos, or other media projects.

Not ideal if you are looking for a simple text-to-speech converter for spoken dialogue, as its primary focus is on singing voice synthesis.

music-production vocal-synthesis audio-creation virtual-artists sound-design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

4,746

Forks

798

Language

Python

License

MIT

Last pushed

Mar 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MoonInTheRiver/DiffSinger"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.