Stable Audio Open

by Stability AI

About the model:

Music generation model

Model type:

Audio

Model performance class:

Full

Link to the model:

https://github.com/Stability-AI/stable-audio-tools

Base models:

(undefined)

End model:

stable-audio-open-1.0

End model license:

(undefined)

About the organisation:

(Not available)

Link to the organisation:

https://stability.ai/

Model release date:

July 2024

Availability

Base Model Data

Requires user information and login to access the data

https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/fma_dataset_attribution2.csv

End User Model Data

Requires user information and login to access the data

https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/fma_dataset_attribution2.csv

Base Model Weights

Requires user information and login to access model weights

https://huggingface.co/stabilityai/stable-audio-open-1.0/tree/main

End User Model Weights

Requires user information and login to access model weights

https://huggingface.co/stabilityai/stable-audio-open-1.0/tree/main

Training Code

https://github.com/Stability-AI/stable-audio-tools

Documentation

Code Documentation

https://github.com/Stability-AI/stable-audio-tools/blob/main/README.md

Hardware Architecture

Preprint

Preprint published on arXiv.

https://arxiv.org/abs/2407.14358

Paper

Peer-reviewed paper published in ICASSP 2025.

https://ieeexplore.ieee.org/abstract/document/10888461

Modelcard

https://huggingface.co/stabilityai/stable-audio-open-1.0

Datasheet

Access

Licenses

Stability AI Community License, Not an OSI approved license.

https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE.md

Is this information not up to date?

Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 April 2026, website content last updated 11 March 2026.