Stability AI

Audio model · United States ·May 2026

Stable Audio 3.0

Audio Open (Restricted)

2.7B

Parameters

About Stable Audio 3.0

Stable Audio 3.0 is an AI model developed by Stability AI, in the audio category, released in 2026, made available as an open-weights model with 2.7B params. A family of four text-to-audio music/SFX latent-diffusion models (Small SFX, Small, Medium 1.4B, Large 2.7B params) trai.

On this page you'll find Stable Audio 3.0's full specifications. Review provider pricing and benchmark scores below, or compare Stable Audio 3.0 head-to-head with other audio models.

→ More models by Stability AI → All audio models → AI benchmarks leaderboard

Run Stable Audio 3.0 locally — what fits

GPUs with enough VRAM to hold Stable Audio 3.0 at FP16 (lower precision needs less), from best value to most headroom. Generation speed depends on your tool, resolution and step count, so we don't estimate it.

fits at FP16 · ~4.1 GB headroom

See fit detail →

Better

AMD Ryzen AI Max+ 395

Consumer GPU · ~$1,999

128 GB VRAM

fits at FP16 · ~108.3 GB headroom

fits at FP16 · ~165.9 GB headroom

See fit detail →

VRAM fit only — we don't estimate generation speed for image/video/audio models (it depends on the tool, resolution and steps).

Community

Would you run Stable Audio 3.0 again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Stable Audio 3.0

Stable Video 4D 2.0 (SV4D 2.0)

Stability AI

Stable Point Aware 3D (SPAR3D)

Stability AI

ControlNet (SD 3.5 Large) Blur

Stability AI

ControlNet (SD 3.5 Large) Depth

Stability AI

ControlNet (SD 3.5 Large) Canny

Stability AI

Stable Diffusion 3.5 Medium

Stability AI · 2.5B

Frequently asked questions

What is Stable Audio 3.0? ▶

A family of four text-to-audio music/SFX latent-diffusion models (Small SFX, Small, Medium 1.4B, Large 2.7B params) trai It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Stable Audio 3.0? ▶

Stable Audio 3.0 was developed by Stability AI and released in 2026.

Is Stable Audio 3.0 open source or proprietary? ▶

Stable Audio 3.0 ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Stable Audio 3.0 cost? ▶

Pricing for Stable Audio 3.0 depends on the provider. See the providers table on this page for the latest API rates.

How does Stable Audio 3.0 perform on benchmarks? ▶

Benchmark scores for Stable Audio 3.0 are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.