verifier.org

ACE-Step 1.5

mit-licensed, self-hosted, vocals in fifty languages, and a full song in under ten seconds on a 3090.

free#developers-who-want-musi

the most permissive licence in the category and the only one you can audit line by line — with no vendor to hold responsible for anything.

plain mit, no revenue threshold, no attribution requirement, no field-of-use restriction. that is more permissive than stability's community licence, which cuts off at $1m of revenue, and vastly more so than meta's musicgen, whose weights are cc-by-nc-4.0 and therefore non-commercial — a fact that catches people who assume 'meta open-sourced it' means they can ship it.

the capability is not a consolation prize. it generates 10 seconds to 10 minutes of audio, handles lyrics and vocals in over 50 languages, includes a vocal-to-backing-track function, and runs in under 10 seconds on a consumer 3090. the maintainers report it outscoring suno v5 on the songeval benchmark, which is their claim rather than an independent one.

the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.

pricing
free
website
github.com
our verdict

the most permissive licence in the category and the only one you can audit line by line — with no vendor to hold responsible for anything.

we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.

more ai music models

LALAL.AI

stem separation and voice extraction rather than generation

#stems#separation

Loudly

royalty-free generated tracks with a licence attached, plus an api

#royalty-free#api

SOUNDRAW

generates unlimited variations you edit by section, licence included

#editor#licence

Eleven Music

we checked this$6/mo

the only one that licensed its training data before launching instead of after being sued.

#anyone-putting-generated#who-would-rather-not-fol