
A steady loop
Beats like “Rain Notes” barely change across 30 seconds, which is a fair thing to ask this demo to try.
Type a sentence and hear instrumental music start to play within the same run. A free community demo, ready below.
MusicGen is Meta’s open text-to-music model from 2023. It doesn’t produce realistic singing, and Meta released its trained weights for non-commercial use only, under CC-BY-NC 4.0. This community demo uses the small version and makes 10 to 30 seconds.
A community member built this demo with the small version of MusicGen. It isn’t Meta’s, it runs on free Hugging Face machines that can be busy, and it costs no credits.
Open on Hugging FaceMusicGen writes the instruments and has no idea what a chorus is for, so ask for a sound. The picture is 30 seconds of “Quiet Hours”, solo piano from our generator, about as long as this demo can go.

The demo’s own example reads “a cheerful country song with acoustic guitars”.
A lower streaming interval, from 0.5 to 2.5 seconds, plays sooner and takes more work.
The seed slider runs from 0 to 10. Move it to get a different result from one sentence.
Two more first-30-second pictures from our generator: enough to judge a groove, and short for a video.

Beats like “Rain Notes” barely change across 30 seconds, which is a fair thing to ask this demo to try.

The bright strip along the bottom of “Cold Bells” is the bass. Listen on proper speakers, since it’s the first thing a small model gets wrong.
Meta’s own demo can’t be placed on other sites, so here’s how the three compare. You can open it on Hugging Face.
| This community demo | Meta’s demo | Our maker | |
|---|---|---|---|
| Length | This community demo: 10 to 30 seconds | Meta’s demo: Up to 120 seconds | Our maker: 2 to 4 minutes |
| Singing | This community demo: No | Meta’s demo: No | Our maker: Yes, or switch it off |
| Paid use of results | This community demo: No | Meta’s demo: No | Our maker: Yes, once you’ve paid |
| Cost | This community demo: Free | Meta’s demo: Free | Our maker: 10 credits for 2 songs on V6 |
Not for anything commercial. Meta’s code is open under MIT, but the trained weights are CC-BY-NC 4.0, which rules out commercial use. Monetized channels and ads are a poor fit.
Not in a way you’d mistake for a person: its makers say it can’t produce realistic vocals. If you need words sung, look at ACE-Step, DiffRhythm or our maker.
Meta’s demo blocks being placed inside other sites, so this page loads one built by a community member, Sanchit Gandhi. It uses the small MusicGen model and streams its audio.
Its author says it works best in Chrome, so try that first. A long wait may also just be the queue on Hugging Face’s shared machines.
Not covered here.Ask us something else
Our maker writes full-length instrumentals. Once you’ve bought any plan or pack, you can use them in paid work.
Make instrumental musicTwo free songs, no account needed.