Audio presentations of a media content delivered onto a device are interrupted using commands not otherwise known to or programmed in to a messaging application used to present the content to the user of the device. In one embodiment, an electronic message having textual content is received at the mobile device, where it is translated into an audio stream, and presented (i.e., played back) to the user of the device within the messaging application. The user provides, and the application receives a string of identical user commands that are not specifically defined or programmed in as commands within the messaging application, and playback of the audio stream is modified according to the received string of user commands.