User engagement computer system and method of using same

A computer-implemented method for automatically providing, by a user engagement computer system comprising one or more computers, images related to audio detected during a video chat session comprising substantially simultaneous presentation of audio and video between two or more user devices in communication with the user engagement computer system, wherein the two or more user devices are each associated with a different user and each one of the two or more user devices has a respective audio sensor, a respective video sensor, a respective motion sensor, a respective screen, and an interactive audiovisual player, the method comprising:

• (a) receiving, by the user engagement computer system, audio input from at least one of the two or more user devices;
• (b) automatically detecting, by the user engagement computer system, from the audio input, first words or first phrases that are spoken during the video chat session;
• (c) selecting, by the user engagement computer system, from a content database that is stored in non-transitory computer-readable memory that is operably connected to the user engagement computer, a first supplementary video element related to the detected first words or first phrases to be transmitted by the user engagement computer system to the two or more user devices;
• and
• (d) transmitting, by the user engagement computer system to the two or more user devices, the first supplementary video element related to the detected first words or first phrases to be displayed in a respective first portion of the respective screen of the two or more user devices during the video chat session,
• wherein the first supplementary video element comprises a first supplementary video segment and a second supplementary video segment,
• wherein the first supplementary video segment and the second supplementary video segment each comprises respective animations that depict a storyline that is related to the detected first words or phrases,
• wherein the first supplementary video segment is displayed and animated simultaneously in each of the respective first portions of the respective screens of the two or more user devices during the video chat session,
• wherein the second supplementary video segment is displayed and animated simultaneously in each of the respective first portions of the respective screens of the two or more user devices during the video chat session, and
• wherein the first and second supplementary video segments are displayed and animated in each of the respective first portions of the respective screens of the two or more devices overlapping in time.