Be the Beat

Dance has traditionally been guided by music throughout history and across cultures, yet the concept of dancing to create music is rarely explored. In this paper, we introduce Be the Beat, an AI-powered boombox designed to generate music from a dancer’s movement. Be the Beat uses PoseNet to describe movements for a large language model, enabling it to analyze dance style and query APIs to find music with similar style, energy, and tempo. In our pilot trials, the boombox successfully matched music to the tempo of the dancer’s movements and even distinguished the intricacies between house and hip-hop moves. Dancers interacting with the boombox reported having more control over artistic expression and described the boombox as a novel approach to discovering dance genres and choreographing creatively. Be the Beat creates a space for human-AI collaboration on freestyle dance, empowering dancers to rethink the traditional dynamic between dance and music.

Co-designed with Ethan Chang in Professor Marcelo Coelho's class 4.043 Design Intelligence at MIT. Ethan Chang, Zhixing Chen, Jb Labrune and Marcelo Coelho, Be the Beat: AI-Powered Boombox for Music Suggestion from Freestyle Dance, TEI '25.