Stability AI Stable Audio 3 open-source audio
Key Questions
What is Stable Audio 3.0?
Stable Audio 3.0 is Stability AI's new open-source audio generation platform featuring multiple music and sound models. It is designed for developers and musicians with fast, high-quality output.
What are the key capabilities of Stable Audio 3.0?
The platform supports up to six-minute song generation and includes an on-device small model. It comes with four music and sound models plus additional variants for varied use cases.
Is Stable Audio 3.0 open source?
Yes, Stable Audio 3.0 is released as an open-source platform with models, technical report, and benchmarks available on Hugging Face and the Stability AI site.
Where can developers access Stable Audio 3.0 models?
Models, the technical report, and extra resources are available in the Stability-AI/stable-audio-3 repository on Hugging Face. A blog post and Discord community are also provided.
How does Stable Audio 3.0 align with current AI trends?
The release follows the trend of domain-specific open models and multimodal capabilities. It provides both large and small on-device variants for flexible audio generation.
New open-source audio generation platform with technical report and models including benchmarks. Aligns with domain-specific open releases and multimodal trends.