Deployed at: jive-nsbe.firebaseapp.com

Have you ever wondered what tunes you could spin up exploring specific frequencies? Jive.ai looks at exploring the interpolation of sounds between two chord-key pairs. Based off the interpolation between frequency pairs, a two-step generative AI process is followed, using a combination of VAEs(Variational auto encoders) and RNNs(Recurrent Neural Nets) to generate tunes that sound real and beautiful.

Find the code here: https://github.com/MadhavKanna/Jive.ai

The generative models are provided by Majenta.js, and I've taken heavy very heavy inspiration from the ideas at https://magenta.tensorflow.org/js-announce

This is a Next.js project bootstrapped with create-next-app. If you want to run this app locally, do the following:

First, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.