Stable Audio represents the cutting-edge audio generation research by Stability AI’s generative audio research lab, Harmonai. We continue to improve our model architectures, datasets, and training procedures to improve output quality, controllability, inference speed, and output length.
Stability AI introduces their AI model for creating audio and music. You can try it out now: https://www.stableaudio.com/
It looks like most of the training data was electronic music, but when the model releases people should be able to fine-tune it to different things.
What’s the audio equivalent of hands, I wonder?
From that drum solo sample, it seems like cymbal crashes.