To provide audio information regarding locations within a geographic area, a client device provides an interactive three-dimensional (3D) display of panoramic street level imagery for a geographic area via a user interface. The panoramic street level imagery includes one or more landmarks. The client device receives a request for audio information describing a selected landmark within the interactive 3D display, and obtains the audio information describing the selected landmark from a server device in response to the request. Then the client device automatically presents the received audio information describing the selected landmark.