Talented musicians can deliver a powerful emotional experience to the audience by skillfully modifying several musical parameters, such as dynamics, articulation, and tempo. Musical robots are expected to control those musical parameters in the same way to give the audience an experience comparable to listening to a professional human musician. But practical control of those parameters depends on the type of musical instrument being played. In this study, we describe our newly developed music dynamics control system for the Waseda Anthropomorphic Saxophonist robot. We first built a physical model for the saxophone reed motion and verified the dynamics-related parameters of the overall robot-saxophone system. We found that the magnitude of air flow is related to the sound pressure level, as expected, but also that the lower lip is critical to the sound stability. Accordingly, we then implemented a music dynamics control system for the robot and succeeded in enabling the robot to perform a music piece with different sound pressure levels.