TPSTokens Per Second

Stable Audio 3 Medium

Stability AI🇬🇧 United Kingdom
active
Compare with other models →

Version History

mediummajor

Initial release of Stable Audio 3 Medium with 2B parameters, supporting variable-length audio generation up to 6+ minutes with sub-2-second inference times on H200 GPU.

Coverage

model releaseStability AI

Stability AI Releases Stable Audio 3 Medium: 2B-Parameter Audio Generation Model with 180-Second Output in Under 2 Secon

Stability AI has released Stable Audio 3 Medium, a 2 billion parameter latent diffusion model capable of generating variable-length audio up to 380 seconds. The model generates music and sound effects in less than 2 seconds on an H200 GPU, trained on 1.28 million licensed and Creative Commons audio recordings.

2 min read
Stability AIaudio generationlatent diffusion