[New Add-on] Vision Assistant Pro: Your Interactive AI Copilot for NVDA (Powered by Gemini)

By mahmood, 2 December, 2025

Forum
Windows

Hello AppleVis community,

I am Mahmood, and I am excited to share Vision Assistant Pro, a new open-source add-on for NVDA. This tool is designed to bring the intelligence of Google Gemini directly into your screen reader to solve digital challenges that usually require sighted assistance.

It is completely free to use (with your own API key) and focuses on interactivity rather than just static descriptions.

🌟 Key Features:

  • 👁️ Interactive Vision (Object & Full Screen): Unlike standard OCR that just reads text, this feature lets you "see" and "ask."

    • Object Vision: Take a snapshot of the specific control (icon, button, image) under your navigator cursor.
    • Full Screen Vision: Scan the entire screen layout.
    • The Best Part: After the initial description, you can chat with the AI. You are not limited to one description; you can ask follow-up questions like "Is there a save icon?", "Describe the chart in detail," or "What color is the button?"

  • 🧠 Smart Translator (Auto-Swap): Instantly translates selected text. It creates a seamless bilingual experience by automatically detecting languages. If the source matches your target language, it intelligently swaps them.

  • 🎙️ Smart Dictation: A powerful voice typing tool. It doesn't just transcribe; it listens, fixes your grammar, removes stutters (ums and ahs), adds punctuation, and types the polished text directly into your active window.

  • 🔓 CAPTCHA Solver: Struggling with visual codes? Press a shortcut, and the AI will solve the math or read the characters and automatically type the result for you.

  • 📄 Document QA: Have a PDF, TIFF, or text file? You can "chat" with your documents. Ask the AI to summarize them, extract specific data, or explain complex sections.

🛠️ Requirement: You need a free Google Gemini API Key to run this add-on.

📥 Download & Installation: You can download the add-on directly from GitHub:

Download Vision Assistant Pro v6.5.1 (Direct Link)

Just open the downloaded file and confirm the installation in NVDA.

🔗 Project Source Code: https://github.com/mahmoodhozhabri/VisionAssistantPro

I developed this to help our community become more independent. I would love to hear your feedback and suggestions.

Best regards, Mahmood

Options

Comments

By treky fan on Tuesday, June 16, 2026 - 00:06

Hi there! I got the app to work, but I have a question. How can I describe an image I come across on a website? Also, to descirbe youtube videos, do you have to click on the link itself beffore getting the video described?

By Brian on Tuesday, June 16, 2026 - 03:34

hi,

What I tend to do is press my hot key to activate this add-on, then press the letter O.
Then I wait a tick for OCR to finish, and it will start to describe pretty much everything on the screen. Immediately I start typing to ask the AI a question, in this case, I might ask something like, "describe the image after the third heading."

HTH.

By Keith on Wednesday, June 17, 2026 - 21:04

Just gave this a try. Amazing! I was able to get descriptions of unlabeled buttons on a web site where NVDA's OCR would not work. Very impressed by this and what it might be able to do to help get past certain inaccessible controls.

By mahmood on Thursday, June 18, 2026 - 06:27

Hi Keith,

Thank you so much for your kind words and for sharing your experience!

Helping users get past unlabeled buttons and inaccessible web controls was exactly one of the main goals I had in mind when developing Vision Assistant Pro. It is incredibly encouraging to hear that it is helping you navigate these barriers where traditional screen reader OCR falls short.

I really appreciate your support. Take care!

Best regards,
Mahmood

By mahmood on Thursday, June 18, 2026 - 06:32

Hi Brian,

I wanted to reach out and express my sincere gratitude to you for actively helping other users and answering their questions in the community.

Seeing you explain the features so clearly and guide others (such as explaining how the incremental QA/Describe and Ask flow works) is incredibly heartening. Your active support and helpfulness give me great motivation to keep working on, refining, and improving Vision Assistant Pro.

Thank you again for your valuable contributions and for being such a supportive part of this journey!

Best regards,
Mahmood