Update March 26, 2024
I've just released what I'm tentatively calling Version 1 of both my Describe Screenshot and Describe Photo shortcuts.
They can both be found on their new dedicated site!
Some of the new changes include:
1. conversations: You can now reply to the descriptions you are provided. to do so, press the okay button on the description's alert. Have nothing to say? No worries! Hit cancel, and the Shortcut will leave you in peace!
2. Slash commands: When typing a reply, you can use /save with either Shortcut, and the last photo or screenshot taken will be saved to the photo album of your choosing. Additionally, Describe Photo also has /add, which will allow you to take another picture to accompany your replies.
3. Describe Photo now supports the Apple Vision Pro! If you run the shortcut on Vision Pro, it will grab the latest photo from your camera roll rather than having you take one. This is because the Shortcuts app on Vision Pro doesn't support taking photos in shortcuts. If you intend to use this shortcut with other smart glasses or prefer to take your photos in the Camera app, you can make grabbing the latest photo the default behavior in the set up screen.
That's everything. Share and Enjoy!
Update
The original describe screenshots shortcut has been updated. the update can be found here.
Now, the set up process walks you through all the parameters you can adjust, like the system prompt and temperature.
Defaults are provided so messing with those fields is optional.
The reason I added those fields to the set up screen was so you no longer have to manually edit the shortcut to change any of those values.
There is also a new shortcut, called Describe Photo, which can be found here.
This one, unlike Describe Screenshot, will take a picture using your camera when run, then get that image described, and yes, it will work with your mac's webcam too.
Just like Describe Screenshot, it can be assigned to a VO gesture or your action button or whatever you want.
Additionally, it will work with the share sheet and Quick Actions menu so you can share images from other apps, or if on a Mac, you can use the context menu for an image (within Finder or other apps) to send images to the Shortcut.
Original Post
Hi all!
Over the last couple days, I've been working on a Shortcut for iOS / Mac OS to quickly describe Screenshots.
Yes, we have Be My AI, and yes, we have the Chat GPT app if we have a Plus subscription, but neither are all that efficient when dealing with Screenshots.
Anyway, if you want to check it out, you will need to click on this link from an iOS or Mac OS device.
When installing the Shortcut, it will ask you for an OpenAI API Key, so you'll want to log into and / or sign up at platform.openai.com,
Create an API Key, and fund the account with at least a dollar.
This can be done on the settings page, under Billing.
Once you've added your key to the shortcut and hit install, all you have to do is assign the Shortcut to a VoiceOver gesture of your choosing and you're good to go.
to do that, head to settings, Accessibility, VoiceOver, Commands, All Commands, Shortcuts, and select the Describe Screenshot Shortcut. You'll then be able to assign it to a VO gesture, keyboard shortcut, or both.
Once you've done that, you can run the Shortcut anywhere, a screenshot will be taken, and the Shortcuts app will open and place you in a textbox where you can include a question to accompany the image, then you can just tap Done when you're ready to send the image over, and a description should come back within 15-30 seconds.
While the image is being processed, you can keep using your phone (Or Mac.) The description will pop up around the top center of your screen, or on your Mac, you'll need to use the Window chooser to switch to the Quick Look Panel that will have opened.
At the end of each description, you'll be told how much that request cost. In my experience, it's usually been around 2-3 cents.
Oh, I almost forgot!
If you want to use it with VO on the Mac, you would go to VO preferences, commanders, and assign it to the keyborad / Trackpad/whatever commander of your choosing. Then you'll be able to run it anywhere you want!
I hope this is useful to you guys! Let me know what you think!