Music generation AI 'Stable Audio 3.0' unveiled, with a large model capable of generating music longer than 6 minutes and a smaller model that runs on smartphones.
Stability AI, an AI company known for developing the image generation AI 'Stable Diffusion,' has released its music generation AI, ' Stable Audio 3.0 .'
Stable Audio 3.0 | Generative Audio Models — Stability AI
Stable Audio 3.0, the model family built with open-weight models
— Stjob AI
https://stability.ai/news-updates/meet-stable-audio-3-the-model-family-built-for-artistic-experimentation-with-open-weight-models
Stable Audio 3.0 is released in four versions: 'Stable Audio 3.0 Small,' 'Stable Audio 3.0 Small SFX,' 'Stable Audio 3.0 Medium,' and 'Stable Audio 3.0 Large.' Three of these versions—'Stable Audio 3.0 Small,' 'Stable Audio 3.0 Small SFX,' and 'Stable Audio 3.0 Medium'—are available as open models and are free to download. The features of each model are as follows.
Stable Audio 3.0 Small: Capable of generating music up to 2 minutes in length. A compact model that works with smartphones and laptops. Ideal for generating short tracks.
Stable Audio 3.0 Small SFX: Capable of generating music up to 2 minutes in length. A compact model that works with smartphones and laptops. Ideal for generating sound effects.
Stable Audio 3.0 Medium: Capable of generating music up to 6 minutes and 20 seconds in length. Enables advanced musical expression.
Stable Audio 3.0 Large: Capable of generating music up to 6 minutes and 20 seconds long. The highest-performing model in the series.
Stable Audio 3.0 also supports operations such as 'editing existing songs' and 'generating continuations of existing songs.' You can also adjust the sound to your liking using LoRA.
'Stable Audio 3.0 Small,' 'Stable Audio 3.0 Small SFX,' and 'Stable Audio 3.0 Medium' are available at the following link.
stabilityai/stable-audio-3-small-music · Hugging Face
https://huggingface.co/stabilityai/stable-audio-3-small-music
stabilityai/stable-audio-3-small-sfx · Hugging Face
https://huggingface.co/stabilityai/stable-audio-3-small-sfx
stabilityai/stable-audio-3-medium · Hugging Face
https://huggingface.co/stabilityai/stable-audio-3-medium
Additionally, the AI generation tool ' ComfyUI ' now supports music generation with Stable Audio 3.0.
Stable Audio 3.0 is now Day-0 supported in ComfyUI.
— ComfyUI (@ComfyUI) May 21, 2026
Open-weight music models (fully licensed data)—from quick SFX and short tracks to longer, more musical pieces—inside the workflows you already use. pic.twitter.com/27qbFBzOKD
Stable Audio 3.0 Large is available via the Stability AI API , and enterprise-向け models are also offered.
Related Posts:
in AI, Posted by log1o_hf