CloudVision

The add-on provides a description of photos, for example, a 23-year-old girl with blonde hair smiling, text recognition, text translation into another language and reading QR codes.

Add-on settings.

Open NVDA menu, Preferences, CloudVision Settings.

Keyboard shortcuts

• NVDA + CTRL + I - recognize the navigator object or the selected file in Explorer. If you press twice quickly, the result will appear in the virtual viewing window.
• the gesture is not assigned - copy the last result to the clipboard. To assign, see NVDA menu, Preferences, input gestures, CloudVision category.

For the navigator, just set it to the desired element, press the combination and the add-on will recognize it. For a file, select it in Windows Explorer without opening it, immediately, without opening the file, press the combination. Only JPG, PNG, GIF are supported. I did not add a PDF, since recognition can last 40 minutes or longer.

The idea and code for the selected files is taken from the "Nao (NVDA Advanced OCR)" add-on.