Model · Music and sound

MusicGen

Meta's downloadable model that turns a short English description, optionally with a hummed or played tune, into instrumental music clips. Cannot sing. Weights are for non-commercial use only and need a strong graphics card.

Go to MusicGen’s website

At a glance

Open or closed
Downloadable, with conditions
You can download and run it, but the licence limits use
Weights downloadable but non-commercial (CC-BY-NC 4.0); code MIT.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence
CC-BY-NC 4.0 (weights); MIT (code) (Non-commercial only)
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?
No
  • You must credit the maker
Weights licensed CC-BY-NC 4.0: non-commercial use only, with credit.
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
AudioCraft docs: at least 16 GB GPU memory for medium models; smaller GPUs can do short clips or the small model. Demo Space on Hugging Face and Colab. Platforms inferred from Python tooling.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed
Technical
source · checked 12 Oct 2026 · checked on the maker's own page
Made by
Meta AI (FAIR team)
No location stated on the model card.
source · checked 12 Oct 2026 · checked on the maker's own page
Status
Available
Released June 2023; no newer version or deprecation noted.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

text to audioaudio to audio

Model card: makes music from text; cannot make realistic vocals; trained on English descriptions; may fade to silence at the end.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

No paid plans listed.

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

Related

Where you can run it

Hugging Face

Other options for “Music and sound, background music”

ACE-Step, Adobe Firefly, AIVA, BandLab SongStarter, Beatoven.ai, Boomy, Captions, DeeVid AI, Eleven Music, Filmora, FlexClip, getimg.ai, Google Flow Music, Google Flow Music (formerly MusicFX), Google Flow Music (formerly Riffusion), ImagineArt, Loudly, Lyria 2, Magic Hour, Mubert, Mureka, MyEdit, Picsart, Replicate

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.