Model · Music and sound

YuE

A free, downloadable model that turns your lyrics and a style description into a full song with singing and backing music, in English, Chinese, Japanese, Korean and more. Needs a powerful graphics card and technical setup.

Go to YuE’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Code and weights released under Apache 2.0; training data not released (not stated in README).
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Apache License 2.0 (Permissive (e.g. Apache 2.0, MIT))
Apache 2.0 adopted 2025-01-30.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes
README invites artists to use outputs freely in their own works; credit 'YuE by HKUST/M-A-P' and an 'AI-generated' label are encouraged, not required.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free to download and run yourself
Plans below.
How you use it: On your own computer, Through another service
Weights on Hugging Face (m-a-p). Windows via community Pinokio installer. Needs CUDA 11.8+. About 360 s per 30 s of audio on an RTX 4090.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
source · checked 12 Oct 2026 · checked on the maker's own page
Made by: HKUST and M-A-P (Multimodal Art Projection)
README says the project is co-led by HKUST and M-A-P; no country stated.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Latest README news item is LoRA finetuning support (2025-06-04).
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

Music and sound, a full song with vocals (main use)

text to audioaudio to audio

Lyrics to full song with vocal and accompaniment tracks; community add-ons offer song continuation.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Rights and safety

Real faces and voices: Copies a real voice (reference-audio style prompt (ICL)), no consent step
ICL mode follows a reference vocal track; README does not frame it as voice cloning and has no consent check.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Where you can run it

Hugging Face

Other options for “Music and sound, a full song with vocals”

ACE-Step, ComfyUI, Eleven Music, Google Flow Music, Google Flow Music (formerly MusicFX), Google Flow Music (formerly Riffusion), Loudly, MiniMax Audio, Mureka, MyEdit, Replicate, Soundverse, Suno, Udio, WaveSpeedAI

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.

YuE