Google open-sources StreetReaderAI, a multimodal map app for blind street exploration

jonfroehlich · x · 2026-11-18

Google Research has released StreetReaderAI, an open-source multimodal map application for non-visual exploration of street-level imagery, built with and for blind and low-vision (BLV) users. Users navigate street images via keyboard or voice, hear real-time descriptions of their location, and ask follow-up Q&A about the surroundings.

The project began as a hackathon effort by Jon Froehlich, Shaun Kane and Alex Fiannaca nearly two years ago. It is open source under Apache 2.0 and can be run locally or loaded in Google AI Studio, aimed at HCI researchers and developers of accessible AI tools.

Original post →

More from Multimodal

Multimodal channel →