Over at Stability AI, my team launched Stable Audio, a new product for AI music generation.
It’s the first product to give people a way of generating music using today’s state-of-the-art AI models for commercial use. It uses latent diffusion to generate original audio based on a text prompt and a duration, delivered in 44.1 kHz stereo. It’s designed to be used by musicians who want to generate samples to use in their own music.
We were really pleased with its reception - it was covered in Music Business Worldwide, Music Ally, and a range of other places.