LIMA AI is a free NVDA add-on. Press a shortcut and NVDA speaks a clear, AI-written description of whatever is on your screen, then keeps you posted as web pages change, all without leaving NVDA.
Three steps to get started
Step 1. Install: in NVDA, open Tools then Add-on Store, search LIMA AI, and install. Step 2. Sign in: open NVDA Preferences, Settings, LIMA AI, and sign in with Google. Step 3. Use it: press NVDA+Alt+D to describe your screen, or NVDA+Alt+W for web narration.
Press NVDA+Alt+D and NVDA speaks a brief, factual description of your active screen. Great for images, dialogs, and anything a screen reader cannot read on its own.
Press NVDA+Alt+W and LIMA quietly narrates changes on a web page as they happen, without interrupting what you are reading, and without repeating itself.
Choose your replies in English or Tagalog, so descriptions feel natural to you.
No API keys. You sign in with Google, and LIMA handles the AI for you.
Zero Data Retention. AI providers may not store or train on your screenshots.
On demand only. A screenshot is sent only when you press a shortcut, never in the background.
Works with NVDA 2023.1 or later on Windows. A free Google account is used to sign in.
No. LIMA does not train on your data, and Roscommon Systems follows a Zero Data Retention policy for all of our products.
No. The add-on is built to fit into NVDA. The shortcuts are announced the first time you run it, and you can change any of them in NVDA's Input Gestures.
No, however you can express your interest in an offline version on our contact us page.