The add-on allows you to get a description of the image using artificial intelligence.
It works through the service visionbot.ru which uses recognition technologies from Google, Microsoft and, more recently, Be My AI from Be My eyes.
The add-on settings are in the NVDA menu, parameters, CloudVision Settings.
Keyboard shortcuts:
- NVDA+CTRL+I - get a description of the navigator object or jpg/png file if it is in focus in Windows explorer. If you press twice quickly, the result will appear in the virtual viewer, you can read with arrows, select, copy, and so on.
- Copy the last recognized result to the clipboard - the combination is not assigned, you can assign it yourself in the input gestures.