I recently came across a forum thread mentioning that Siri can describe what’s on your screen. That got me thinking: if Siri already has this capability built in, why not package it into a simple Shortcut and trigger it with a VoiceOver gesture? This way, there’s no need to deal with API keys, tokens limits, or third‑party services.
So I tried it — and it works perfectly on my iPhone 15 Pro Max, with zero API keys or extra setup. Now I’m curious whether it works just as smoothly for others.
I’m sharing the Shortcut below. If you have a moment, please try it out and let me know how it behaves on your device and iOS version:
👉 Shortcut link:
https://www.icloud.com/shortcuts/c137b61525684f1f90058db9f301d6a3
How to use it:
1. Install the Shortcut (named Screenshot Describer).
2. Go to Settings > Accessibility > VoiceOver > Commands > All Commands > Shortcuts.
3. Assign Screenshot Describer to your preferred VO gesture.
What I’ve observed so far:
• It’s much faster than any dedicated description app I’ve tried.
• If I open the Camera app and trigger the gesture, it instantly takes a screenshot of the viewfinder and describes what the camera sees — great for quick real‑world object descriptions.
• I may create another version that takes a photo directly instead of screenshotting the camera preview.
The best part: I didn’t write a single line of code. This was all done through the Shortcuts app using suggested actions and variables.
Note: The Shortcuts app still has some VoiceOver quirks — UI elements sometimes stop being read, and certain functions require long‑pressing or navigating inconsistent actions. So creating a shortcut is a bit painful. Might require a bit of patience.
Let me know how it works for you.
By SeasonKing, 23 January, 2026
Forum
iOS and iPadOS