Inspiration

Our team is a diverse group with a shared passion for technology and music. The concept for Infinitune was born out of a desire to bridge the gap between music, coding & generative AI. Our vision was to create a tool that would allow users to generate unique music samples using simple text inputs, thus opening up a new world of possibilities for creativity and expression.

What it does

Infinitune is an innovative tool that brings a unique text-to-code-to-audio approach to music sample generation. Users enter a textual description, and Infinitune translates this into executable SuperCollider code, which in turn synthesizes into the desired music sample. This could be anything from drum beats to basslines to melodies.

How we built it

Infinitune was built using a robust stack that includes Node.js, Express.js, ngrok, Next.js, React, Tone.js, GPT-4, and SuperCollider. Our main tool was the OpenAI GPT-4 model, which we used to convert the user's text into SuperCollider code. The server was implemented using Node.js, Express.js, and ngrok, which handled the API calls between the frontend (developed with Next.js) and the backend where the AI model was running.

Challenges we ran into

We first attempted to fine-tune the GPT-4 model to directly generate music samples, but this approach didn't yield the desired results. We pivoted to querying GPT-4 with examples of music samples we liked, which then guided the creation of new samples. Another challenge was the unexpected departure of a team member on the final day of the hackathon. However, we were able to adapt and take on additional responsibilities.

What we learned

Our journey in creating Infinitune has been a whirlwind of learning and growth. We discovered the nuances of working with AI, particularly the GPT-4 model, and its potential applications in music production. We explored the fascinating intersection of music and coding, experimenting with the potential of a text-to-code-to-audio approach. Furthermore, the experience highlighted the power of adaptability and resilience.

What's next for Infinitune

The potential of Infinitune extends far beyond the realm of sample or music production. With its ability to convert textual descriptions into unique audio samples, Infinitune has a vast array of applications across multiple industries. From enhancing live streams with on-the-fly event/alert sounds to scoring scenes for movies, from generating dynamic sound effects for video games to customizing audio for podcasts, content creation, and comedy routines, the possibilities are endless. Furthermore, it can be used for audio branding, allowing businesses to create custom jingles that align with their brand identity. It can even contribute to immersive user experiences in AR/VR applications, art installations, and exhibitions. As we advance, we aim to continue refining and expanding Infinitune's capabilities to tap into these exciting opportunities.

Built With

Share this project:

Updates