abv1 · SA3 engine

Text→audio and audio→audio with Stable Audio 3. Shared backend for the abv1 music-AI demos; also exposes headless /generate and /generate_a2a endpoints.

Model

Small Music — 0.6B, fast (seconds per gen) Medium — general audio, higher quality

Prompt

Negative prompt (optional)

Seconds · max 120

1 120

Output

Powered by Stability AI. Models are used under the Stability AI Community License; see NOTICE.md in this repo. All audio here is AI-generated — not real releases by any artist.