Complex Computing Network For Customizing A Visual Representation For Use In An Audio Conversation On A Mobile Application

Systems, methods, and computer program products are provided for generating visual representations for use in audio conversations. For example, a method comprises receiving user information associated with a first user; receiving visual representation information input by the first user, wherein the visual representation information comprises a first feature, wherein the visual representation information further comprises a second feature distinct from the first feature, wherein the first feature comprises a facial feature; generating a visual representation based on the visual representation information, wherein the visual representation is presented to a second user during an audio conversation between the first user and a second user, wherein at least one of the first feature or second feature changes form when the first user speaks during the audio conversation, and wherein both the first feature and the second feature remain static when the second user speaks during the audio conversation.