Cypher - The Diss Track AI

Inspiration

This project was created as a merger of multiple ideas. We thought about creating a security system, which relied on an AI to grant entry. The combination of this with the music industry produced the idea of a diss track generator.

What it does

Cypher takes an image of the user through the webcam, analyses this, and produces a diss track based on the user’s appearance and demeanour.

How we built it

Cypher was built using several programming languages, frameworks, APIs and image tagging methods. Firstly, we learnt how to send POST requests via networks to retrieve the webcam image from the website. Next, we experimented with VQA transformers to tag image data but ended up using existing models. Meanwhile, another member of our group developed knowledge of further APIs, such as the Uber Duck & OpenAI APIs, to generate lyrics and synthesise this into a song. Finally, we implemented these using Flask and designed a GUI.

Challenges we ran into

A major challenge we faced was that not all of our members were familiar with using APIs. Furthermore, we originally intended to allow users to retaliate but had difficulty with speech recognition. Given more time, we would allow users to do this and the best rap would be determined by a judge agent, which we developed.

Accomplishments that we're proud of

We successfully implemented a working end product that is easily accessible, and simple to use.

What we learned

Over the course of this project, we learned how to make use of multiple APIs, such as MediaAPI, OpenAI API and UberDuck API, to name a few

What's next for Cypher - The Diss Track AI

The original concept involved the user also writing their own diss track, and another AI judging which diss track is better. Due to time constraints this wasn’t achievable, but if we were to continue working on this project, this feature would be something we would include.