The score-driven approach to time series modeling provides a solution to the problem of modeling circular data and it can also be used to model switching regimes with intra-regime dynamics. Furthermore it enables a dynamic model to be fitted to a linear and a circular variable when the joint distribution is a cylinder. The viability of the new method is illustrated by estimating a model with dynamic switching and dynamic location and/or scale in each regime to hourly data on wind direction and speed in Galicia, north-west Spain.