• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
multimodal-art-projection avatar

YuE

Open music generation model that plans a score, then sings the song

  • AI media
  • AI models and runtimes
View on GitHub
Website

What it is

YuE2 is an open-weights music model that turns lyrics and a style prompt into a melody-and-chord score, then renders it as a full stereo song with vocals and accompaniment. Because the score is explicit, a person or an AI agent can read and edit it before rendering, and transcribed recordings can be reworked into covers in a new style. Musicians, researchers, and hobbyists run it locally through a staged Python API, ComfyUI nodes, or an agent skill to compose, cover, and revise songs.

Images

Facts

Stars
12,394 GitHub stars.
12,394

Forks
1,422
Commits
190
Contributors
13
Language
Python
License
Apache-2.0
Last commit
Oct 6, 2026
On GitHub since
January 2025
First release
September 2026
Platforms
Linux, library
Self-hostable
No
Alternative to
Suno, Udio
Tags
  • agent-skills
  • music-generation
  • open-weights
  • voice-cloning
  • local-ai

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.