Auto-completion for content expressed in video data

Abstract

The present disclosure provides a computing device that performs an auto-completion process that generates and inserts text of spoken content of a video into a text entry field. By providing quoted content in a text input field, a system can mitigate the need for users to perform the tedious process of listening to spoken content of a video and manually entering the spoken content into a computing device. In some configurations, a system can receive one or more keywords from a user input and identify spoken content containing the keywords. The system can provide text of the spoken content based on a level of relevancy and populate one or more input fields with the text of the spoken content. The generation of auto completion text from spoken content of a video can enhance user interaction with the computer and maximize productivity and engagement with a video-based system.