Technologies for generating a media compilation include comparing video metadata associated with a video to audio metadata associated with a plurality of digital songs to determine one or more matches between the compared metadata. The metadata defines various characteristics of the corresponding video and digital songs, and each match is indicative of a similar characteristic of the video and a corresponding digital song. One or more sync points are generated based on the determined matches and one or more songs are selected based on the sync points. The sync points may be prioritized based on the characteristics associated with the sync point and/or the degree of similarity. The video and the selected digital song(s) are subsequently compiled based on the associated sync points.