Abstract: A system, method, and computer-readable media are described for facilitating generation and/or presentation of sound images. In one embodiment, a method of facilitating generation of sound images includes receiving a user selection of an image from a video. A user selection of an audio portion from the same video is also received. The selected image and the selected audio portion are associated with one another as a sound image such that the selected image and selected audio portion can subsequently be simultaneously presented as a still image with background audio.