Stable Audio 3

Name: Stable Audio 3
Author: fal

other

Stable Audio 3 Small Music audio-to-audio is a 459 million parameter latent diffusion model that transforms input music into new variations up to 2 minutes guided by text prompts.

Capabilities

Show unsupported (8)

No supported capabilities recorded.

Details

Model IDfal-ai/stable-audio-3/small/music/audio-to-audio

Providerfal

Creatorfal

Family—

License—

Statusactive

Typeother

Input modalities—

Output modalities—

Open weight—

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2026-05-22

Sourceofficial

API

GET/v1/models/fal/fal-ai/stable-audio-3/small/music/audio-to-audio

Stable Audio 3

fal-ai/stable-audio-3/small/music/audio-to-audio

Stable Audio 3 Small Music audio-to-audio is a 459 million parameter latent diffusion model that transforms input music into new variations up to 2 minutes guided by text prompts.

Changes · 3 entries

fal-ai/stable-audio-3/small/music/audio-to-audiocreateca7a400Nov 2, 2026, 03:02 AM

fal-ai/stable-audio-3/small/music/audio-to-audioupdate53ef452Jul 9, 2026, 02:32 AM

last_seen_at2026-06-03→2026-07-01

fal-ai/stable-audio-3/small/music/audio-to-audiocreated68a4f1Jun 10, 2026, 02:10 AM