The Waseda Flutist Robot WF-4RIV is a humanoid robot that is able to imitate a human flute performance. In the recent years the mechanical construction of the robot has been improved, so that the robot’s playing capabilities have reached the level of an intermediate human instrument player. To make the robot able to play at this performance level, careful calibration of its musical parameters is necessary. Using the flutist robot’s core control software, this procedure is very complicated to perform. In this paper we present the implementation of a visual control interface that allows also non-technical users to calibrate the sound settings. The newly developed control interface enables a musician to adjust certain parameters of the robot performance while the robot is playing. Experiments in which we verify the functionality of this sound calibration system are presented. We examine the visual processing system’s perception of the instrument movements of a human performer and analyze their effect on the performance of the robot.