A system is configured to synchronize a first video, a second video, and an audio track. The system analyzes image content associated with the first video and the second video to obtain a first subset of images of the first video and a second subset of images of the second video. The system then determines a music beat of the audio track to be synchronized with one of the first subset of images or the second subset of images. The system then adjusts a framerate of the first subset of images or the second subset of images based on the determined music beat to synchronize the first subset of images or the second subset of images. The first subset of images and the second subset of images may then be combined, which the system then plays back from a designated playback slot along with the audio track.