Model · Music and sound

ACE-Step

A free, downloadable model that writes whole songs, with or without vocals, from a text description and lyrics. It can also remix or re-sing parts of a track. You need a decent graphics card and some technical setup.

Go to ACE-Step’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
Weights and code released under Apache 2.0.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Apache License 2.0 (Permissive (e.g. Apache 2.0, MIT))
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes
Apache 2.0 allows commercial use of the model. The model card says nothing specific about generated music; avoid copying real artists or songs.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: Free to download and run on your own computer
Plans below.
How you use it: On your own computer
Third-party hosts and finetunes exist but were not verified from the maker's pages.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: ACE Studio and StepFun
Model card names ACE Studio and StepFun as joint makers; no country stated.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Weights still published; the model card mentions no successor. Newer versions may exist but were not checked (fetch budget).
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)
Music and sound, a changed, longer or remixed version of a song
Music and sound, background music

text to audioaudio to audio

Full-song generation from a description and lyrics; remixing, style transfer, lyric editing, repainting and extending. Vocals described by the maker as coarse.

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

Limits: note: No hard length limit; maker says songs over 5 minutes may lose structure. About 20 seconds to make a 4-minute song on an A100.
source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Hugging Face

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

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, YuE

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.