Stability AI Releases a Sound Generator
Stability AI, the startup behind the AI-powered art generator Stable Diffusion, has released an open AI model for generating sounds and songs. The model, called Stable Audio Open, takes a text description and outputs a recording up to 47 seconds in length. It was trained using around 486,000 samples from free music libraries Freesound and the Free Music Archive.
Stable Audio Open can be used to create drum beats, instrument riffs, ambient noises, and “production elements” for videos, films, and TV shows. It can also be used to “edit” existing songs or apply the style of one song to another. A key benefit of this open-source release is that users can fine-tune the model on their own custom audio data. For example, a drummer could fine-tune samples of their own drum recordings to generate new beats.
However, Stable Audio Open has some limitations. It cannot produce full songs, melodies, or vocals, and Stability AI suggests that users looking for those capabilities opt for the company’s premium Stable Audio service. Additionally, the model cannot be used commercially, as its terms of service prohibit it. The model also does not perform equally well across musical styles and cultures or with descriptions in languages other than English, which Stability AI attributes to biases in the training data.
Stability AI has faced controversy recently after its VP of generative audio, Ed Newton-Rex, resigned over a disagreement with the company’s stance that training generative AI models on copyrighted works constitutes “fair use.” The release of Stable Audio Open appears to be an attempt to address these concerns while promoting Stability AI’s paid products.
As music generators gain popularity, copyright issues are becoming a central point of focus. Recently, Sony Music sent a letter to 700 AI companies warning against “unauthorized use” of its content for training audio generators. Additionally, a law aimed at tamping down abuses of AI in music was signed into law in Tennessee in March.
source: https://techcrunch.com/2024/06/05/stability-ai-releases-a-sound-generator/
