Model · Music and sound

Stable Audio 2.5

Stability AI's closed music and sound model. Makes tracks up to three minutes from a description, reworks uploaded audio, or continues a track you start. Trained on licensed music; outputs can be used commercially.

Go to Stable Audio 2.5’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
No weights released; on-premises only under an enterprise licence.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Licence: Stability AI Terms of Service and Acceptable Use Policy (The maker's own terms)
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?: Yes
Commercial use permitted on all hosted plans and the API, subject to the Terms and AUP; announcement calls it 'commercially safe' and trained on a fully licensed dataset.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: 50 credits once when you sign up to the Stable Audio app
Plans below.
How you use it: Maker's own API, Through another service, In your browser, Inside another tool
StableAudio.com, Stability API, partners fal, Replicate and ComfyUI; on-premises with an enterprise licence.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Some setup
Easiest through the Stable Audio app; the API needs coding.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Stability AI
No company location stated on pages read.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Announced 10 September (2025 by context).
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

Music and sound, background music (main use)
Music and sound, sound effects
Music and sound, a changed, longer or remixed version of a song

text to audioaudio to audio

Text-to-audio, audio-to-audio and inpainting (continue an uploaded track from a chosen point). Vocals not mentioned.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

No paid plans listed.

Credit price page rendered by script. Also usable in the Stable Audio app (see that entry) and via fal and Replicate. Free credits: kb.stability.ai subscription article.

source · checked 12 Oct 2026 · inferred or from a secondary source; needs review

Rights and safety

Limits: max audio seconds: 180
Under two seconds to generate on a GPU, per Stability.
source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Stable Audio, fal, Replicate, ComfyUI

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, MusicGen, MyEdit, Picsart

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.