An audio processing system includes a memory, and a processor. The processor is coupled to the memory, and, when executing a program stored in the memory, performs: receiving a first voice that is a voice uttered by a first speaker; determining whether or not a position of the first speaker can be identified; and outputting, to a target device, a voice command that is specified by a voice and is a signal for controlling the target device, the processor limiting output of a speaker position command related to a position of a speaker among the voice command in a case where the processor determines that the position of the first speaker cannot be identified.