AtlasAI Center AI tool intelligence
stabilityai · Open-weight model

stable audio 3 medium

stable audio 3 medium is a text-to-audio model published on Hugging Face by stabilityai.

Downloads (30d)
134,775
Released
May 17, 2026
Specifications

stable audio 3 medium specs

Provider
stabilityai
Type
Open-weight model
Model ID
stabilityai/stable-audio-3-medium
Task
text to audio
Released
May 17, 2026
License
other
Architecture
stable-audio-3
Base model
stabilityai/stable-audio-3-medium-base
Downloads
134,775Hugging Face, last 30 days
Likes
643
Languages
English
Popularity
18/100134,775 Hugging Face downloads in the last 30 days
Source
Hugging Face
Overview

About stable audio 3 medium

stable audio 3 medium is an open-weight model from stabilityai, released on May 17, 2026, with the other license, 134,775 Hugging Face downloads in the last 30 days.

Specs are sourced from Hugging Face and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.

FAQ

stable audio 3 medium questions

When was stable audio 3 medium released?

stable audio 3 medium was published on May 17, 2026.

Can I run stable audio 3 medium locally?

stable audio 3 medium is published as an open-weight model on Hugging Face under the other license, so you can download the weights and run them on compatible hardware, subject to the license terms.