An image processing system includes an information processing apparatus and an image processing apparatus connected to each other via a network. The information processing apparatus has an application installed thereon to give a new function to the image processing apparatus. The image processing apparatus transmits to the information processing apparatus, voice data obtained by a microphone of the image processing apparatus and data set via an operation screen customized according to the application. The information processing apparatus determines answer information indicating an action to be taken by the image processing apparatus, based on the received voice data, a dictionary owned by the application and the data set via the operation screen, and then transmits the determined answer information to the image processing apparatus. The image processing apparatus takes an action according to the answer information received therefrom.