Robotic motion generation methods using machine learning have been studied. Bilateral control-based imitation learning can imitate human motions using force information. Using this method, variable speed motion generation that con-siders physical phenomena such as the inertia and friction can be achieved. However, the previous study focused on a simple reciprocating motion. To learn the complex relationship between the force and speed more accurately, it is necessary to learn multiple actions using many joints. In this paper, we propose a variable speed motion generation method for multiple motions. We considered four types of neural network models for the motion generation and determined the best model for multiple motions at variable speeds. Subsequently, we used the best model to evaluate the reproducibility of the task completion time for the input completion time command. The results revealed that the proposed method could change the task completion time according to the specified completion time command in multiple motions.