Mechanisms are provided to automatically identify referenced assets in real-time streaming communications and automatically identify, retrieve, and present these assets during the real-time streaming communication. The mechanisms obtain, in real-time, a textual representation of a user's input during the real-time streaming communication. As part of a
background process to the real-time streaming communication, computer
natural language processing is executed on the textual representation to identify
key terms or key phrases from the textual representation. The computer
natural language processing is specifically configured to identify
key terms / phrases corresponding to references to assets. As part of the
background process, one or more search queries are generated and executed to search for a matching asset based on the identified
key terms / phrases. As part of the real-time streaming communication, the matching asset is presented to participant computing devices of the real-time streaming communication.