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.
More from Multimodal
- Rumble-2-Flash: open-weights speech-to-text model handles accents, noise and 40+ languages — omarsar0 · 2026-11-18
- Runway cuts real-time 57B video model serving from 8 H100s to 4 with inference optimizations — runwayml · 2026-11-18
- Open-weights ASR model Rumble-2-Flash hits #9 on Hugging Face Open ASR leaderboard, 40+ languages — cneuralnetwork · 2026-11-18
- Gemini 3.5 Transcribe adds real-time voice-command editing for dictation — AI_Andrew · 2026-11-18
- Antipode: An Open-Source Local Synth Controlled via MCP, Turning Agent Ideas into WAVs — Dizzy_Basil6892 · 2026-11-18
- Audio EQ and compression inside Antigravity: Gemini 4 builds in-chat FFmpeg console — alexanderchen · 2026-11-18