Skip to content

Stability AI · Music

Stable Audio 3 Medium

Stability AI 🇬🇧MusicStable Audio family
From Empiriolabs's listing:
Stability AI text-to-audio model for music and sound effects, 44.1 kHz stereo clips up to 380 seconds, with length, step and seed controls.
Listings
10
Providers
4

Evidence and sources

Released 20 May 2026Maker HQ: GB (according to Stability AI's own website)
Sources: EmpirioLabs data, llminfo researchPrimary data from EmpirioLabs from llminfo research: release date

Input & output

as stated by the model's providers
Text
Audio

Capabilities

Supported operations and provider-stated features

Audio input

Listings

 NanoGPTstable-audio-3/medium/text-to-audio · text-to-audioSource: NanoGPTNot published by the provider$0.0414
 Empiriolabsstable-audio-3-medium · FP16Source: EmpirioLabs dataNot published by the provider$0.035

8 listings without a price are hidden.

Benchmarks

No benchmark scores yet.

Also known as: fal-ai/stable-audio-3/medium/audio-inpainting, fal-ai/stable-audio-3/medium/audio-outpainting, fal-ai/stable-audio-3/medium/audio-to-audio, fal-ai/stable-audio-3/medium/text-to-audio, stable-audio-3-medium-audio-inpainting, stable-audio-3-medium-audio-outpainting, stable-audio-3-medium-audio-to-audio, stable-audio-3-medium-text-to-audio, stable-audio-3/medium/text-to-audio

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works