The company has been struggling with its business and recently faced controversy when its VP of generative audio resigned over a disagreement regarding the use of copyrighted works in training generative AI models. Stability AI claims that the limitations of Stable Audio Open, including biases across musical styles and cultures, are due to the training data. The release of Stable Audio Open seems to be an attempt to change the company's narrative while also promoting its premium Stable Audio service.
Key takeaways:
- Stability AI has released an open AI model, Stable Audio Open, that generates sounds and songs using text descriptions. The model was trained on approximately 486,000 samples from royalty-free music libraries.
- The AI model can be used to create drum beats, instrument riffs, ambient noises and production elements for videos, films and TV shows. It can also edit existing songs or apply the style of one song to another.
- Despite its capabilities, Stable Audio Open has limitations. It cannot produce full songs, melodies or vocals, and it is not optimized for commercial use. It also has biases due to the training data, performing less well with certain musical styles and languages other than English.
- Stability AI, which has been struggling with its business, recently faced controversy after its VP of generative audio resigned over a disagreement regarding the use of copyrighted works in training AI models. The release of Stable Audio Open is seen as an attempt to change this narrative.