A computing device may receive video content along with first audio content that is synchronized with the video content. The computing device may also receive second audio content that is not synchronized with the video content. The computing device may, in turn, transmit output content that includes the video content and the second audio content. A second portion of the second audio content may be identified that has second audio characteristics that are within a selected range of similarity to first audio characteristics of a first portion of the first audio content. A temporal offset may be calculated between the first portion and the second portion. The video content and the second audio content may be synchronized within the output content by delaying, by an amount of the temporal offset, a transmission of the second audio content relative to a transmission of video content.