https://www.infoq.com InfoQ Digital Signal Processing News feed https://www.infoq.com/news/2023/10/stable-audio/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Digital+Signal+Processing-news <img src="https://res.infoq.com/news/2023/10/stable-audio/en/headerimage/generatedHeaderImage-1695556023477.jpg"/><p>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.</p> <i>By Anthony Alford</i> Deep Learning Neural Networks Generative AI Digital Signal Processing AI, ML & Data Engineering news Tue, 10 Oct 2023 14:00:00 GMT https://www.infoq.com/news/2023/10/stable-audio/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Digital+Signal+Processing-news Anthony Alford 2023-10-10T14:00:00Z /news/2023/10/stable-audio/en