Google Maps Uses Gemini to Suggest Captions for Photos
April 7, 2026 – 5:48 pm
Google Maps has introduced a new feature powered by Gemini, its AI model, that suggests captions when users share photos of places. This initiative aims to streamline the process of sharing user-generated content on the platform.
Currently, available in English on iOS in the United States, with an upcoming global rollout to Android, the feature analyzes uploaded photos and videos, identifying subjects and contexts to generate captions. Users can accept, edit, or delete these suggestions.
How Gemini Captions Work
The process is simple: when a user selects a photo or video for sharing, Gemini examines the image, recognizes the subject and surroundings, and proposes a caption. This caption serves as a starting point, allowing users to customize it before posting.
This new tool is presented as an assistive feature rather than automation, emphasizing that the generated captions are suggestions and not definitive outputs. This approach maintains user trust and aligns with Google’s content standards, ensuring accountability for any potential inaccuracies.
Building on Existing AI Features in Google Maps
This captioning feature builds upon several recent Gemini-powered enhancements to Google Maps:
- November 2025: Landmark-based navigation, providing directions like "Turn after the Thai Siam Restaurant."
- January 2026: Cycling and walking guidance assisted by Gemini.
- March 2026: Introduction of Ask Maps, a conversational search mode leveraging community reviews, and Immersive Navigation, described as a significant upgrade to driving directions.
By integrating AI into various aspects of the platform, Google aims to enhance user experiences and maintain the quality of its vast repository of user-generated content.