kinda expensive IMHO if I would use it so often like be my eyes.

its pretty useful regardless faster than openning be my eyes

I didn't make this because Be My AI can't describe screenshots well.
I made it because you can't bind Be my Eyes to a VO gesture like you can this shortcut.
This isn't a replacement for Be My AI. It's just a quicker way of getting things described.
The shortcut does have a couple advantages that Be My AI doesn't though. For one, you can adjust the system prompt, temperature, and other parameters, which is really useful.
Plus, with the Shortcut, you can include a message with your image, so the message and image are processed together. This is a really powerful thing which Be My AI doesn't support, but should.
Oh and also, the this shortcut will work on Mac OS. Be My AI does not.

Of course. Just about any modern iOS app can be sideloaded onto an Apple Silicon Mac, but as you pointed out, these almost always come with limitations which make the experience with the app far from pleasant.
If it can't access finder extensions or the share sheet what can you use it for? Do you just use it to take pictures from your webcam?
Given these limitations, I would still argue that you can't realistically run the Be My AI service on a Mac even if the app will technically run.

I get not wanting to spend money on image descriptions but it's cheaper than you probably realize.
I've been sending dozens of images over the past two days while testing and while playing games and I don't even think I've spent a dollar yet.

Just out of curiosity, what pictures have you ever felt the need to take from the Mac? Seems rather inconvenient, though I suppose it could be useful if you wanted to get a close-up view of your face or something. Also, I’m fairly sure the WebCams on max are quite a bit worse than phone cameras these days, but I might be wrong and I’m too lazy to compare them right now.

@11 because I don't have a life or any responsibilities, I have yet to need a serious reason to use be my AI. Yeah I'm that unproductive.
I think the phone camera is loads better, but the mac does allow for a wider picture I would imagine. I could be wrong about that. And just like the angle of the phone, you have to consider the angle of the laptop lid. So personally I think it's just a different method of doing things with the same or nearly the same result.

That makes a lot of sense. I totally agree using the phone is easier. That I was never trying to dispute. I personally like using the phone a lot more. I'd much rather be able to import photos into be my ai on the mac rather than take them on the fly for analyzing. Your tool would definitely be useful for that, but I don't have any pictures or really care about it. So for me it is not applicable. It's awesome that we at least have some options for the mac. And envision is a thing, but I have 0 knowledge on how accessible it is, how good it is, and the functionality it supports on the mac. If it only uses the rear facing camera, then it is useless, assuming you can't import photos.

speaking of those things, I wonder, is it possible to extract the API key from be my AI and use it for this? I mean, it's fair use anyway, since it's not sold to anyone or whatever, but maybe that could work as a stop gap till these things become cheaper, or for people who are in unsupported countries, or those who don't have a credit card, or...etc?

I mean, it would be fair use only if the key is kepped on the computer of the one who discovers it, and even if it gets shared, it's done responsibly, like in any piracy community, there are rules to this stuff as well. I could start reverse engineering be my eyes for android, but yeah, you're right, probably it's further protected. O really, the API key isn't scoped to only chat gpt, and even then only image mode? I thought that's possible, but apparently not, so yeah, I can see why it might not be considered fair use

oof, good I didn't go through with it then, since it appears to be against their ToS

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!