An object of the present invention is to suppress occurrence of a combination inhibition error when an instruction of changing setting values of a plurality of setting items is given by a voice operation. An image processing device according to one aspect of the present invention has: an instruction receiving unit receiving a change instruction by a voice operation, for set setting values of a plurality of setting items; a setting order control unit, in the case where combination inhibition occurs by changing the set setting values of the plurality of setting items in a setting order based on the change instruction, changing the setting order of changing the set setting values to a setting order in which the combination inhibition does not occur; and a setting changing unit changing the set setting values of the plurality of setting items in the changed setting order.