Google Home is rolling out a new feature in 2026 that lets Gemini AI trigger smart home automations based on what security cameras detect, the company announced on May 27th. The update is part of a broader set of improvements to Gemini for Home, which launched in early access in October.
“Because your cameras can now actually understand what they see, your smart home can automatically react to almost anything happening around your home,” Google said in its announcement.
Users can describe a scene or event in natural language — such as “raccoons near the trash bins” or “red BMW enters driveway” — and select which cameras should watch for it. When the condition is detected, a pre-set routine activates automatically. Examples include turning on security lighting, opening smart blinds, or adjusting a heating system. The feature also works with specific people if the Friendly Faces feature is enabled.
Google notes the camera requires a brief processing delay before reacting, and advises against using it for “instant alerts, time-sensitive situations, or security and safety purposes.”
The feature currently supports Nest cameras and select third-party cameras with “Gemini Built-In.” It is limited to English-speaking users in the United States who are enrolled in the Google Home Public Preview program. Users must also enable AI descriptions through “Gemini for Home camera features” and subscribe to the Google Home Premium Advanced plan, priced at $20 per month or $200 per year.
Google also announced that Gemini for Home can now execute multiple actions from a single voice command — such as lowering blinds, dimming lights, setting a timer, and starting a podcast simultaneously. The assistant is also said to respond more quickly and deliver more consistent replies to natural language requests.
The camera-triggered automation capability may expand access to more users over time, though Google has not announced a broader rollout timeline.
Source: The Verge