gan.style is a website that lets you resynthesize audio from YouTube using a neural net trained on vocal and instrumental recordings. The result is an A.I. interpretation of the audio which retains the pitches and rhythms of the original but adds the texture and timbre learned from the training set.
You can listen to one of our many pre-rendered videos, or paste in your own YouTube URL to hear it processed through a couple of our models. gan.style makes use of our Inference API to transform the audio pulled from youtube through the model of your choice.
Beta API Access
Currently we are using the Inference API in a number of our projects, and are opening it up to private beta users. If you have a need for something like this, please fill out the form below and we’ll get back to you soon.