An electronic device for providing graphic data based on a voice, and an operation method therefor are provided. The electronic device includes a display, and a processor, and the processor is configured to obtain at least one keyword from a voice signal related to a plurality of images, determine at least one graphic data corresponding to the at least one keyword, select at least one of the plurality of images, based on a point in time at which a voice corresponding to a keyword that corresponds to the determined graphic data is output, and perform control so as to apply the determined graphic data to the at least one selected image.