Audio generation Stability AI Pro and up

Stable Audio3 Medium

3 Medium

Stable Audio 3 Medium audio-to-audio is a 1.4 billion parameter latent diffusion model that transforms an input audio clip into new stereo variations up to 6 minutes guided by a text prompt.

Stable Audio 3 Medium sample output
Sample output
Modality
Audio
Maker
Stability AI
Minimum plan
Pro
Credits
417 credits
Availability
Available now

How it works

Generate audios in just a few simple steps

  1. 1

    Sign in to FunAI

    Create a free account - you land back on this model page and can start generating right away.

  2. 2

    Describe what you want

    Write a prompt, tune the parameters, and add any reference input the model supports.

  3. 3

    Generate and download

    Preview and download instantly, then iterate or send the result to the editor.