Hello guys,
I have created the free app PiccyBot that speaks out the description of the photo/image you give it. And you can then ask detailed questions about it.
I have adjusted the app to make it as low vision friendly as I could, but I would love to receive feedback on how to improve it further!
The App Store link can be found here:
https://apps.apple.com/us/app/piccybot/id6476859317
I am really hoping it will be of use to some. I have earlier created the app 'Talking Goggles' which was well received by the low vision community, but PiccyBot is a lot more powerful and hopefully useful!
Thanks and best regards,
Martijn van der Spek
Comments
Having same issue
Getting the same error message when attempting to upload a picture from an app
Sad that issue has returned
I ran into this issue a couple of months ago, and then everything started working again. Let's hope it's a simple fix or just a temporary glitch.
Certificate issue. Will provide update today
Hello all, there is an expired certificate that caused the PiccyBot outage. Will provide an update today. Will look for a more permanent solution that offers both stability and at the same time avoids abuse of the PiccyBot services by other apps.
As soon as the new update is available I will let you know, hopefully later today, if Apple approves it fast.
Updated
Hi all, PiccyBot update has been accepted by Apple and is available in the app store. This should fix the issue. Good luck!
Thanks!
Thank you very much for all of your hard work on this app. It is extremely appreciated. Looking forward to the day when I can use Piccybot hands free with my Meta glasses. :-)
The model list and OpenRouter (or similar)
There are quite a few models in the model list that are not their latest iterations. While newer is not always synonymous with better, in this quick moving field it generally brings some improvement and also for less money, which is just as important. Also, old models get deprecated eventually. Just to name some examples: Gemini 3.5 Flash recently got superceded by 3.6 Flash, GPT 5.5 and earlier is replaced by the 5.6 line of models, there is the new Sonnet 5, etc.. This is not urgent in any way, what we have works well, but to keep the list a bit cleaner, an eventual update would be nice.
Another thing. I recently discovered OpenRouter which, for those that don't know, is basically an API that can connect you to a huge amount of AI models through a single interface (I'm sure there are similar services, but I believe OpenRouter is among the most well known). Anyway, while connecting to many models is handy, the really interesting thing for me, and I would think for the visually impaired community, is that through using their API, you can use variants of even some of the largest AI models with zero data retention, i.e. none of your conversations, images, etc. are saved, not even in abuse monitoring logs etc that is the standard when using the AI companies' APIs. As privacy is very important for us when we want to take pictures/videos of things, here is a way where we can get what only big companies otherwise can get, so this might be something worth looking into, not only for PiccyBot but for other apps as well that want a privacy focus. There is of course a caveat: OpenRouter charges 5.5% extra on top of the usual token costs, but especially for cheaper models this could be very interesting I think.