User guide


In this user guide, you’ll find advice on how to get the most out of Stable Audio, generative AI techniques, information about our AI models and training data.


Get to grips with how to use the Stable Audio user interface.


Text prompts refer to the text you use to describe how you want your audio to sound.

Learn how to get the best audio output using text prompts.


Add audio into the AI generation process to guide the output towards your desired music or sound effects goal.

Prompt structure

Pro tips: curating your text prompts can help you get more out of Stable Audio.

Stable Audio 2.0 Model

Our most advanced audio model yet, enabling you to generate songs up to 3 minutes in length, complete with high-quality structure.

Stable Audio 1.0 Model

Our first state-of-the-art audio diffusion models to generate long form music.

Training data

Our first models are trained exclusively on music provided by our partner AudioSparx.