synth muse

Synth Muse is a quick prototype I made in an afternoon, starting with Omma by Spline. It came from something that had been sitting in my mind for a while. I wanted to make an audio-reactive interactive piece inspired by the visions I get while lying on the floor in the middle of a candlelit hot yin yoga class, as well as by a dream I had when I was 7, and by my love for experimental music and strange, emotional audiovisual worlds.

Under the hood there’s JavaScript, WebGL and GLSL, with a custom audio system that turns typed input into generative notes and layered sound, while the visuals respond in real time through shader-based motion, image warping, glow, ghosting, spectral splitting, particles, animated text and palette shifts. The two character assets were created with ComfyUI.he configurator lets the user shape a lot of the experience directly, from melody intensity, tempo, pitch range and reverb to distortion, glow, blur, parallax, sway, cradle motion, breathing, particle flow and background speed. You can also switch palettes and toggle anime mode, which swaps the character entirely. That part is important to me. I really enjoy building pieces where the user gets to personalize what they’re seeing and, in a way, become a co-creator of the experience.

It still feels like an early piece, and I’d love to keep pushing it further by adding things like audio capture, a vocoder, and a richer shader world around the figure so the whole environment feels even more immersive and alive.

TECHNICAL DETAILS

JavaScript, GLSL, WebGL, ComfyUI