A mobile device, such as a smart phone, receives and presents interactive audio content from an interactive voice response (IVR) system. The mobile device provides an interface that enables a user to navigate through a menu presented in the interactive content. The interface further presents action elements that identify actions that can be requested through the menu, and selection of the one of the action elements may cause the IVR to perform an associated action. For example, the interface may identify representatives at a call center, and a selection of one of the action elements causes the IVR to establish a communication between the mobile device and the selected representative. The action elements may further identify status information associated with the call center, such as an expected wait time.