Responsive to an incoming telephone call, a session server consults pre-stored caller preferences to generate a source file of caller-specific audio content, then conducts an interactive playback session audibly presenting the content to the caller. Each call's source file may include an internally stored history record documenting events that occur during playback, such as caller utterances, identity of audio content presented, voice prompts presented to the caller, errors, and time stamps of various playback events. In response to certain caller utterances or completion of the source file's presentation, the session server may reference the history record for guidance in creating an appropriate follow-up source file containing appropriate supplementary audio content. Use may also be made of history records for purposes such as increasing the functionality of interactive user playback, providing billing records, aiding debugging, and preserving data that is useful for marketing purposes.