Stable Audio Open (stable-audio-tools) at a glance
Checked 16 Oct 2026stable-audio-tools is the code behind Stable Audio Open 1.0 and Open Small, with a basic Gradio UI and training scripts. The model makes instrumental music, loops and sound effects from an English text prompt; its model card says it cannot generate realistic vocals, so it does not write songs. Code is MIT; weights are gated on Hugging Face under the Stability AI Community licence, free for commercial use under USD 1M annual revenue. Hardware and OS support are not documented.
RepoQuarry. “Stable Audio Open (stable-audio-tools).” Checked 16 Oct 2026. https://repoquarry.dev/projects/stable-audio-toolsHow much of Suno does it replace?
1 of 5 jobs. Short instrumental clips and loops only; no vocals or full songs.
For full songs with vocals from a prompt or lyrics, covers and restyles of an uploaded song (Cover), extending or regenerating part of a song (Extend, splitting a song into vocal and instrument stems (Get Stems), see other Suno alternatives. You may also need to build an interface, an API server and hosting yourself.
Facts, with sources
Every answer links to where we found it. We read the documentation; we did not install it.
A basic Gradio interface is provided to test out trained models.github.com · stable-audio-tools#interface ↗ 1d ago
Commercial License: to use this model commercially, please refer to https://stability.ai/licensehuggingface.co · stable-audio-open-1.0 ↗ 1d ago
For researchers, developers, small businesses, and creators with less than $1M in annual revenue.stability.ai · license ↗ 1d ago
once you've accepted the terms for the model on Hugging Facegithub.com · stable-audio-tools#interface ↗ 1d ago
Requires PyTorch 2.5 or later for Flash Attention and Flex Attention support.github.com · stable-audio-tools#install ↗ 1d ago