This paper presents the LoopJam installation which allows participants to interact with a sound map using a 3D com-puter vision tracking system. The sound map results from similarity-based clustering of sounds. The playback of these sounds is controlled by the positions or gestures of partic-ipants tracked with a Kinect depth-sensing camera. The beat-inclined bodily movements of participants in the in-stallation are mapped to the tempo of played sounds, while the playback speed is synchronized by default among all sounds. We presented and tested an early version of the in-stallation to three exhibitions in Belgium, Italy and France. The reactions among participants ranged between curiosity and amusement.