Developer Stable Diffusion has unveiled an AI music generator based on textual descriptions
Stability AI, developer of the Stable Diffusion AI image generator, has unveiled Stable Audio, an AI model that generates short audio compositions based on textual descriptions.
You can listen to examples of the neural network's work and try to create your own music on the service's website. Stable Audio is based on the same basic methods of AI work that Stable Diffusion uses to create images. The model was trained on more than 800 thousand fragments of licensed music from AudioSparks audio library.
The free version of Stable Audio allows you to create up to 20 tracks per month of up to 20 seconds. The commercial plan for $12 per month includes 500 audio files of 90 sec. each. It is noted that the results from the free plan cannot be used for commercial purposes.
What's Your Reaction?