An approach for monitoring interaction between individuals engaged in a communication session is disclosed. The individuals are described herein as a customer service representative and a customer and the communication session is accomplished over a communication network. Audio data embodying the communication session is copied and stored to a media file in conjunction with video data captured by a video capture device monitoring the customer service representative. The media file is a data structure in which the audio data and the video data are stored in segmented fashion. Each segment of audio data is associated with a segment of video data based on a common time reference, thereby providing synchronized documentation of the communication session. The media file is stored on a database and available to a supervisor using a server computer to monitor the communication session for quality assurance or other evaluation purposes.