HelloPixDig

Directory › Audio & voice › YuE

YuE
Image: official project repository

> GEM AUDIO & VOICE · RESEARCH & MONITORING · LOCAL AI

YuE

by Multimodal Art Projection (M-A-P)

An open model that turns lyrics into a full song, vocals and backing track.

11.6 k stars GitHub Apache-2.0 Free when localOpen sourceOpen weightsLocal
View on GitHub →

What it does

  • YuE2 generates 48 kHz stereo audio from lyrics and a style
  • Ships an agent skill to drive song creation from AI agents
  • Apache-2.0 code; CC BY-NC 4.0 weights (commercial use by agreement)

Install it

Requirements: Linux, Python 3.12.

Clone the repository
git clone https://github.com/multimodal-art-projection/YuE.git
Install dependencies
cd YuE && python -m pip install --upgrade pip && python -m pip install .
Generate a first song
python examples/generate.py --output outputs/first-song

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode
Prompt
Install YuE (https://github.com/multimodal-art-projection/YuE) on my machine.
1. Check the requirements: Linux, Python 3.12. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Clone the repository: git clone https://github.com/multimodal-art-projection/YuE.git
- Install dependencies: cd YuE && python -m pip install --upgrade pip && python -m pip install .
- Generate a first song: python examples/generate.py --output outputs/first-song
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.