{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibq7dz4lw5lvhqwjzcrebdferxygbhlmosfm4ziwdjtjy4co6avki",
    "uri": "at://did:plc:mz7h4r2iyp2egghuqaolnsev/app.bsky.feed.post/3mfuntabwbij2"
  },
  "path": "/forum/windows/new-extension-gemini-captcha-solver-ai-powered-image-captcha-resolution-chrome",
  "publishedAt": "2026-02-27T18:40:41.000Z",
  "site": "https://applevis.com",
  "tags": [
    "Download the Extension (ZIP Package)",
    "View Source Code on GitHub",
    "Google AI Studio"
  ],
  "textContent": "Gemini Captcha Solver: An AI-powered solution for screen reader users\n\nHello everyone,\n\nFollowing the release of **Vision Assistant Pro** , which I first shared with this amazing community, I have been working on a specialized tool to tackle one of the most persistent barriers on the web: **Image-based Captchas.**\n\nI am proud to introduce **Gemini Captcha Solver** , a Chrome extension specifically designed to help screen reader users navigate those frustrating alphanumeric image challenges using the power of Google Gemini AI. **I will also soon release this feature for iOS via UserScript.**\n\nWhile many websites are moving towards accessible alternatives, others still rely on visual-only captchas. This tool is my latest effort to bridge that gap and ensure a more independent browsing experience for the visually impaired community.\n\n* * *\n\n### Key Features\n\n  * **AI-Driven Recognition:** Leverages Google's latest Gemini models to accurately interpret and solve alphanumeric captchas.\n  * **Built for Accessibility:** Fully optimized for **NVDA** and **JAWS** using ARIA live regions. The extension provides real-time spoken notifications about the status of the captcha-solving process.\n  * **Proxy Support:** Integrated proxy settings to ensure reliable API connectivity for users in regions with restricted access to Google services.\n  * **Privacy-Centric:** All API keys and configuration data are stored locally within your browser's secure storage.\n\n\n\n* * *\n\n### Installation and Links\n\nThe extension is currently available for desktop Chrome via manual installation. **Please note that I will soon release this feature for iOS via UserScript as well.**\n\n  * **Download the Extension (ZIP Package)**\n  * **View Source Code on GitHub**\n\n\n\n* * *\n\n### Quick Setup Guide\n\n  1. **Get an API Key:** Obtain a free Gemini API key from Google AI Studio.\n  2. **Installation:**\n     * Download and extract the ZIP file.\n     * Open Google Chrome and navigate to `chrome://extensions`.\n     * Enable **Developer mode** (toggle switch in the top right).\n     * Press the **Load unpacked** button and select the extracted folder.\n  3. **Configuration:**\n     * Open the extension settings from your toolbar.\n     * Paste your API key.\n     * Click the **Fetch Models** button to retrieve the available AI models.\n     * Select a model from the list (e.g., Gemini 3.0 Flash).\n\n\n\n* * *\n\n### Feedback Welcome\n\nYour feedback was instrumental in the success of Vision Assistant Pro, and I hope for the same here. If you encounter any bugs, have questions about the setup, or have suggestions to improve its accessibility, please feel free to reach out or open an issue on the GitHub repository.\n\nI hope this tool makes your daily web navigation a little easier!\n\nBest regards,\n\n**Mahmood Hozhabri**",
  "title": "[New Extension] Gemini Captcha Solver: AI-Powered Image Captcha Resolution for Chrome"
}