Skip to content
local-ai

Stable Audio Open 1.0

Stability AI · Audio & music · 1B · Released 19 July 2024

Permitted with conditions TextAudio Open weights

Stable Audio Open generates variable-length audio, up to 47 seconds, in stereo at 44.1kHz, from a text prompt. It was trained on openly-licensed audio (Freesound and the Free Music Archive), and the model card notes it is strongest at sound effects and field recordings rather than realistic singing, and works best with English prompts. At around a billion parameters it is consumer-GPU friendly, though no official VRAM figure is given. The licence is Stability's Community License: free for research and for commercial use by organisations under US$1 million in annual revenue, with an enterprise licence required above that.

Strengths

  • Generates up to 47 seconds of stereo 44.1kHz audio
  • Trained on openly-licensed audio, and strong at sound effects
  • Around 1B parameters, so consumer-GPU friendly

Weaknesses

  • Weaker at realistic vocals than at effects and textures
  • Best with English prompts
  • The Community License adds a revenue-threshold condition for larger organisations

Hardware requirements

QuantisationApprox. VRAMNotes
Native (1B)~6GBApproximate; no official figure. Around a billion parameters, so consumer-GPU friendly

What you'd need to run this

Roughly what a machine to run this would need, at up to three levels of quality. Memory is the deciding factor.

Minimum to run it

Native (1B) · ~6GB needed

One 12GB GPU

NVIDIA GeForce RTX 3060 12GB

or a Mac or mini-PC with unified memory, if you prefer no discrete GPU, Mac mini M5 Pro .

At least 32GB of system RAM alongside the card.

around £700–£1,100

What else 12GB runs →

Licence

Stability AI Community License

Stable Audio Open 1.0: common questions

What hardware do I need to run Stable Audio Open 1.0?
At its most compressed (Native (1B)) it needs roughly 6GB of VRAM, and about 6GB for good quality. VRAM figures are approximate and depend on context length and settings.
Is Stable Audio Open 1.0 free for commercial use?
Commercial use is permitted, but with conditions. Free for research and for commercial use by individuals and organisations with under US$1 million in annual revenue; above that threshold an enterprise licence from Stability AI is required. Read the licence before relying on it at scale.
Can I run Stable Audio Open 1.0 on Apple Silicon?
It can run on Apple Silicon through general runtimes, but it is not specifically optimised for it.

Availability

Recommended for

  • Local sound-effect and audio-texture generation
  • Adding generated audio to a project without cloud services
  • Smaller organisations under the revenue threshold

Related models

Related guides

Glossary

Our coverage

Catalogue entry last verified 18 August 2026. Specifications change; verify anything you are about to spend money on.