Google Home Update Enhances Facial Recognition and Event Descriptions
Quick Look
- Google Home is updating its Familiar Faces feature to identify people even when their faces aren't fully visible, using non-biometric data.
- The library will also auto-update with recent images.
- AI event descriptions can now include specific sounds like barking or footsteps, improving accuracy.
AI-generated summary
Why It Matters
Google is updating its Home app with new features for facial recognition, event descriptions, and system health alerts, aiming to improve accuracy and user experience.
A new update for Google Home could make it less likely your smart home cameras mistake you for someone else, just because you’re facing away from the camera.
Starting June 23rd, Google’s expanding its facial recognition feature so that people you’ve tagged in your Familiar Faces library can continue to be identified when their faces aren’t clearly visible, using “additional non-biometric signals (body size, clothing color, etc.).”
The Familiar Faces library will also begin automatically updating with the most recent images of everyone in your house, so you should get fewer inaccurate notifications from outdated examples.
Google also says its AI-generated video event descriptions “can now identify specific sounds — like dogs barking, alarms, or footsteps” and include them in the notes, even if the audio came from something off camera.
All of these updates could help address some of the quirks The Verge’s Jennifer Pattison Tuohy noticed while trying out Google’s updated smart home system last year, like event logs with detailed descriptions of people who weren’t there, and things that didn’t happen.
A new update to the Google Home app in version 4.20 also adds new “System Health alerts” if your Nest thermostat detects issues with your HVAC, which sounds like a Gemini-connected update to the previously existing Google Nest System Health Monitoring, and improved support for Matter switches.
Open Questions
- What are the specific privacy implications of using non-biometric signals?
- How will the AI handle edge cases with new sound identification?






