A driving sound generation device includes: an acquirer that acquires vehicle information; a storage that stores a plurality of sound source data including driving sound source data and masker sound source data for generating a masker sound; a first adjuster that performs a first adjustment of the plurality of sound source data in accordance with the vehicle information; a second adjuster that performs a second adjustment of at least one of the plurality of sound source data after the first adjustment when the determiner determines that a change amount is smaller than or equal to a predetermined change amount; and a synthesizer that mixes the plurality of sound source data after the second adjustment to generate a driving sound to be output into a cabin of the vehicle; and an outputter that outputs, to the cabin of the vehicle, the driving sound generated.