/ Models

Stable Audio 3

Stable Audio 3 Medium is a 1.4 billion parameter latent diffusion model that generates high-quality stereo music up to 6 minutes from text prompts, trained on fully licensed data for safe commercial use.

Takes
text
Makes
music
Release date
2026-06-03
Licence
commercial

What it costs

The supplier does not state a price on the model itself — check the supplier's page.

Where it runs

Runs through fal, on one key that covers most of the open and licensed media models.

Licence: commercial

Open at the supplier →