(Go: >> BACK << -|- >> HOME <<)

Skip to main content
R
Android will use Gemini Nano AI for TalkBack image descriptions.

At Google I/O 2024 today, Google announced a multimodal version of Gemini Nano, allowing the on-device processing-powered AI model to recognize images, sounds, and spoken language in addition to text.

Those multimodal capabilities are also coming to the Android accessibility feature TalkBack, using AI to fill in missing information about unlabeled images, without requiring a connection to the internet.


Animation showing Google Talkback powered by Gemini Nano AI recognizing an image and describing it for a user as “A close-up of a black and white gingham dress. The dress is shor with a collard and long sleeves. It is tied as the waist with a big bow.”
Google notes that “Description of images may vary.”
Image: Google