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 choreographing creatively. Be the Beat embodies the ambiguity of human and machine creativity, inviting a reexamination of the traditional dynamic between dance and music. With this boombox, the lines between creator and creation, leader and follower, human and AI, are continually blurred.