AIVA

AIVA offers users two ways to create music. First, using pre-trained “preset styles” based on various in-house curated datasets made up of important musical features such as harmonic progressions, rhythmic patterns, and melodic lines. Second, using an uploaded song to influence the composition process into generating something completely unique with similar musical characteristics.

Over the years, the humans behind AIVA have built many AI models—such as recurrent neural networks, convolutional neural networks, and evolutionary algorithms—which enable AIVA’s creativity in the music domain. Modularity is an important part of AIVA’s design, letting artists who collaborate with AIVA interpret, edit, and regenerate AIVA’s creations at will.

AIVA’s creative process can be boiled down to learning from musical data, composing scores, and finally, turning those scores into audio. They use the power of AI to analyze scores and recordings, as well as to generate original compositions. But they rely on a more traditional method of sampling human musicians to produce audio, which adds a necessary human touch to the final product.