Meta patents auto-editing glasses that pick video highlights from speech
Meta describes a system for head-wearable devices that automatically creates highlight reels from recorded video. The method splits video and audio into matching segments, transcribes the audio, and selects moments based on the spoken content to build a final clip.
In the filing’s own words
A method automatically creating a highlight video from video data captured at a head-wearable device is described. The method includes, in response to a capture command, receiving image data captured at cameras of the head-wearable device and receiving audio data captured at microphones of the head-wearable device. The method further comprises causing the image data to be divided into a plurality of image segments, causing the audio data to be divided into a plurality of audio segments, each audio segment of the plurality of audio segments corresponding to a respective image segment of the plurality of image segments, and generating a respective transcription of each audio segment. The method 300 further includes, in accordance with a determination, based on the respective transcription, that a respective audio segment is a highlight segment, add the respective audio segment and a corresponding image segment to a highlight video.
What exactly they claim (claim 1)
1. A non-transitory, computer-readable storage medium including executable instructions that, when executed by one or more processors, cause the one or more processors to: in response to a capture command: receive image data captured at one or more cameras of a head-wearable device; and receive audio data captured at one or more microphones of the head-wearable device; cause the image data to be divided into a plurality of image segments; cause the audio data to be divided into a plurality of audio segments, each audio segment of the plurality of audio segments corresponding to a respective image segment of the plurality of image segments; generate a respective transcription of each audio segment of the plurality of audio segments; in accordance with a determination, based on the respective transcription, that a respective audio segment is a highlight segment, add the respective audio segment and a corresponding image segment to a highlight video.
Facts
- Company
- Meta (Meta Platforms Technologies, LLC)
- Official title
- CONTEXT-AWARE TECHNIQUES FOR VIDEO HIGHLIGHT EXTRACTION INTEGRATING AUDIO ANALYSIS, AND SYSTEMS OF USE THEREOF
- Publication number
- US20260321292A1
- Application number
- 19637286
- Filed
- Apr 2, 2026
- Published
- Oct 15, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G11B 27/036 Physics & computingA61B 5/6803 Human necessitiesG06F 3/013 Physics & computingG06V 10/26 Physics & computingG06V 20/41 Physics & computingG06V 20/49 Physics & computingMore from Meta in Wearables
- Meta patents wristband tech that saves battery by checking hand gestures in two steps Sep 1, 2026
- Meta patents smart glasses that beam your voice to a friend's earbuds Sep 10, 2026
- Meta patents hand gestures that switch controls between watch and headset Sep 1, 2026
- Meta patents wristband that lowers video quality to save battery Sep 8, 2026
- Meta patents wristband that simplifies complex hand gestures Sep 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.