Music and sound

Stable Audio 3.0 Medium

Name: Stable Audio 3.0 Medium
Author: Stability AI

The open-weights mid-size member of the Stable Audio 3.0 family, released 20 May 2026 for full song composition with tracks up to 6:20. Weights are published on Hugging Face under the Stability AI Community License, so it can be self-hosted and fine-tuned.

An audio model by Stability AI · read 2026-08-14 · sourcing medium

Up to: 380 seconds
Weights: Downloadable
API: No
Commercial use: Permitted subject to conditions

Aimed at creators and developers who want local generation without an API dependency.

Commercial use — Permitted subject to conditions

Stability AI Community License (version dated 5 July 2024).

Revenue threshold: free below $1,000,000 in annual revenue, chargeable above it.

Free only below a revenue threshold. Free for 'any individual person or entity' for research, non-commercial and commercial purposes provided they generate less than USD $1,000,000 in annual revenue; 'If at any time You or Your Affiliate(s)... generate more than USD $1,000,000 in annual revenue... any licenses granted to You under this Agreement shall terminate' and a separate commercial licence must be obtained

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Stability AI's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is mixed. Some fields came from pages we retrieved, others could not be confirmed and are left blank. Check the vendor's current documentation

What it takes in: text, audio
What it makes: audio
Maximum duration: 380 seconds
Controls: style-prompting, reference-audio, extend
Weights: Downloadable
API: No
Pricing: Free to download and use under the Stability AI Community License below the $1M annual revenue threshold; Enterprise License required above it.
Released or updated: 2026-05-20

Strengths

Open weights with clear output ownership in the licence text
Long-form generation up to 6:20
Fully licensed training data claim
Free commercial use under $1M revenue

Weaknesses

Licence terminates automatically above $1M annual revenue
'Powered by Stability AI' attribution required when distributing
No indemnification outside the Enterprise License
Sample rate and vocal capability not documented on the pages fetched
The stabilityai/stable-audio-3.0-medium Hugging Face model card returned HTTP 401 and could not be read

Best for

Self-hosted or on-prem music generation
Small studios and indie teams under the revenue cap
Fine-tuning to a house style

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

Duration: 'up to 6:20' per the 3.0 announcement vs 'up to six minutes' on the product page. 380 seconds (6:20) is used.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

Training data and copyright: what is not settled names “indemnification”
Open weights versus closed API: renting or owning the model names “open weights”
LoRAs and fine-tuning: teaching a model your subject names “fine-tuning”
Diffusion models: generation by denoising names “sample”

MCP servers that front Stability AI

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

Audio Analyzer Audio and voice
Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.
Audiolla Music
Self-hosted MCP server: audio stems, mastering, MIR analysis, DSP, MIDI, speech tools.
Civitai Image generation
Civitai MCP.
Cochlea Audio and voice
Render, analyze, and verify audio (WAV/FLAC/mp3/ogg) offline and deterministically via MCP tools.
Comfyui Image generation
MCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM.
Corent Image generation
Generate images and videos via the Corent API, auto model routing with provider fallback.

1 further server name Stability AI with lower confidence and are not listed, because a server naming a vendor may be using it for text rather than media.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Stable Audio 3.0 Large

The flagship closed-weights model in the Stable Audio 3.0 family, released 20 May 2026 and aimed at music platforms and high-volume production. It gen

Music and sound

Stable Audio 3.0 Small and Small SFX

Two open-weight on-device variants released 20 May 2026. Small runs full music composition on a mobile device or consumer laptop with tracks up to two

Music and sound

Stable Audio Open Small

A 0.5B-parameter latent diffusion transformer released 14 May 2025 with Arm, generating up to 11 seconds of 44.1 kHz stereo audio from English text pr

Music and sound

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.