The Kagi Translate app currently supports contextual translation of text in an image (e.g. a real-world photo taken using the camera app). It also supports literal translation of text in a document with a supported format (e.g. TXT, MD, etc.). However, it does not yet support the literal translation of text in an image. Without changing the contextual translation feature associated with the camera app, suggest extending the literal translation feature for documents to also support images (PNG, JPEG, etc.).
Some websites do not support selecting and copying text. There are often cases where the text to be translated is already in an image-like format. Sometimes, simply taking a screenshot of the text to translate is just the most convenient method. The user should be able to directly share the image with the Kagi Translation app using OS menus ("Share with..."). The app should then identify and extract the text contained within the image. The extracted text should then be pasted as input to the normal text translation feature, as if the user simply copy-pasted the text themselves. The extracted and translated text may then be edited (fix mistakes, make tweaks, adjust translation settings, etc.) or copied to the clipboard for further use.
