MoonInTheRiver/DiffSinger
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
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.
Stars
4,746
Forks
798
Language
Python
License
MIT
Category
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.