AI Vision: Gemini Screenshot, Webpage & Multi-Tab AI Assistant for Chrome
Unknown author · Tools
Media
6 items
Description
Gemini AI screenshot assistant, OCR image-to-text, webpage summarizer & multi-tab research copilot for Chrome with your own API key AI Vision is an AI screenshot assistant for Chrome. Select part of a chart, image, error message, or document, ask Gemini what it means, and keep the answer ready for a follow-up. Use it to: • Explain charts, diagrams, interfaces, and error messages • Copy text from screenshots and other images • Summarize a readable webpage while you browse • Compare useful details across supported tabs Get started 1. Install AI Vision from the Chrome Web Store. 2. Create a Gemini API key in Google AI Studio, open AI Vision Settings, and save it. 3. Open an ordinary webpage, choose Capture, select an area, and ask a question. Follow up from the answer; labels may vary in the public v2.5 listing. Browser tasks (Beta) are optional and approval-gated, with a visible Stop action. AI Vision is free to install, but Google controls Gemini access, quotas, and any billing. Gemini can misread small or blurry text, so check important facts. Chrome internal pages, the Chrome Web Store, and other restricted pages cannot be analyzed. Your key and preferences stay in Chrome's local storage. Your prompt and the screenshot or page context needed for a request go directly to Google's Gemini API over HTTPS; there is no developer proxy or analytics. See the privacy notice and source at github.com/stiwarilbj/AI_Vision. AI Vision is an independent project and is not affiliated with Google.