A voice processing device includes a voice recognition unit for extracting a command contained in an input voice, and a control unit for controlling operation of the voice processing device itself and/or instructing external devices to operate, based on the extracted command and/or operation instruction information provided. The control unit stores, in a storage device as an operation history, operation information associating the command or a part thereof and/or the operation instruction information or a part of the operation instruction information with details of the operation which is performed by the voice processing device and/or the external device based on the command and/or the operation instruction information. When a voice is input anew, the control unit extracts from the operation history an operation record containing a command or a part of a command, and controls operation of the voice processing device itself and/or instructs an external device to operate.