[Feature] OCR and then Translate?

[iandol]

The new OCR action and workflow from a screenshot is really cool. It would be great if there was a new action that would allow us to translate the output text using Apple's built-in API too (I's rather not use GPT etc.)

[fortred2]

I think the "Translate Text" Action in Apple Shortcuts uses Apple's built-in or native API. You could create a BTT Action that calls an Apple Shortcut that you create that translates the input text into your desired language.

[iandol]

Thank you @fortred2 — shortcuts indeed has a simple translate shortcut that can work with the clipboard, so this [Translate Clipboard]:

Can then be run by BTT after the OCR:

Awesome stuff!!!

[louishino]

Please take a look at the post I sent. I want to create a feature similar to Safari's, where you can do real-time OCR and translation on images (so you can directly extract text from images on a webpage and translate it).

[fortred2]

What post are you referring to?

[louishino]

Real-time OCR and Translation for All Web Images in Chrome

Currently, BetterTouchTool (BTT) has implemented a feature for quick OCR of screenshots to extract text. Big thanks to Andrew for his brilliant work on this! But we can take it a step further. What we truly need is real-time OCR and translation for all images on a webpage. For reference, those familiar with Safari might already know how this works: When you pause a YouTube video or view an image in a post, you can directly copy the text on the image without needing to take a screenshot first…

[iandol]

One annoyance I faced was 3 new entries in the clipboard when this trigger ran, but I just discovered on another thread there is an action to dis/enable clipboard observation, so cool and clean clipboard history!: