Near Real-Time AI Enhancement of Video or AR Presentations of Live Events (US 2026/0341309)
The Filing
Owner: Microsoft Technology Licensing, LLC
Inventors: David Callaghan, Dinesh Kumar
Filed: April 29, 2025
Published: October 29, 2026
What It Claims
An AI agent listens to a live video stream, picks out spoken words to change based on preset rules or the profile of the person watching, and has generative AI swap in replacement words in both the audio and the video within seconds, smoothing the video and audio before and after each swap so the change is hard to notice. Two viewers of the same stream could be shown different words.
In Their Words
a computing system identifies, from a plurality of spoken words in a live audio recording of individuals speaking, spoken words to modify, based on a set of parameters and/or a profile of a user, using an AI agent.
Status
Pending. Not yet granted.
Status verified November 2026.
Related Filings
US 2026/0341308 A1 (companion filing for recorded video, same inventors, same day)
