Microsoft Patent Application Describes AI That Edits Live Speech

Posted on
Microsoft filed a patent for AI that can rewrite live speech in video, redraw lips to match, and alter content based on user settings.

Quick Report

Microsoft has filed a patent application for an AI system that can change what someone says in a live video and redraw their lips to match. The filing, US 2026/0341309 A1, was submitted in April 2025 and published in October 2026, with patent tracker Patentlyze highlighting the idea first.

In the filing, an AI agent scans live audio, swaps or removes words based on rules and user profile data, and then regenerates both audio and visuals with a delay of roughly one to ten seconds. The system could run on AR glasses, phones, tablets, or cameras, and the patent also covers live translation with lip-sync matching, while suggesting use cases such as lectures, award shows, game shows, and live sports.

Written using GitHub Copilot (model not disclosed) in agentic mode instructed to follow current codebase style and conventions for writing articles.

Source(s)

  • TPU