© REUTERS/Dado Ruvic/Illustration
The race to dominate the AI music scene is heating up, and Meta is throwing its hat in the ring with a new tool that could revolutionize how we create music. Meet JASCO, a new AI model that converts simple chords or beats into full-fledged musical tracks, giving creators unprecedented control over the final product.
Meta’s FAIR team, responsible for this innovative tool, describes JASCO as comparable to other AI music generators but with better and more flexible controls over the generated music. And they’re not just talking the talk – Meta has released a collection of music clips showcasing JASCO’s impressive capabilities, proving that this isn’t just another AI hype train.
But Meta isn’t keeping all the fun to themselves. They’re releasing the code behind JASCO under an MIT license, allowing other AI developers to build upon this groundbreaking technology. This move reflects Meta’s commitment to collaboration within the global AI community, recognizing the importance of shared knowledge and innovation in this rapidly evolving field.
JASCO follows in the footsteps of Meta’s previous AI music creation tool, MusicGen, which could generate 12-second tracks from text prompts. MusicGen, however, also had the ability to use melodies as input, making it the first AI tool capable of turning a melody into a full-fledged song. JASCO takes this concept to the next level, offering greater control and versatility.
These innovations stand in contrast to AI music platforms like Udio and Suno, which generate entire tracks solely from text prompts. While these platforms have become increasingly popular, they have also raised concerns within the music industry due to suspicions that they may have been trained on copyrighted music without authorization.
