Stability AI Releases Generative Audio Model Stable Audio

Harmonai, the audio research lab of Stability AI, has released Stable Audio, a diffusion model for text-controlled audio generation. Stable Audio is trained on 19,500 hours of audio data and can generate 44.1kHz quality audio in realtime using a single NVIDIA A100 GPU.

a100 a100 gpu ai anthony audio audio generation data deep learning diffusion diffusion model generate generative generative-ai gpu harmonai lab ml & data engineering neural networks nvidia nvidia a100 nvidia a100 gpu quality realtime releases research stability stability ai stable audio text