Abstract: An interactive voice response (IVR) system adaptor causes the media player of an IVR system to present a user with a first option to proceed with an audio-only call and a second option to experience a multimedia call including display of visual information on the user device. When the user selects the first option, the proxy IVR interface passes first messages output from the media player to an application server of the IVR system, and passes second messages from the application server to the media player. When the user selects the second option, the IVR system adaptor receives third messages from the user device, translates the third messages into the first messages, passes the first messages to the application server, in response thereto receives the second messages from the application server, converts the second messages to fourth messages, and sends the fourth messages to the user device.