Use PiccyBot to convert photos into spoken descriptions, pose questions in the text field, and zoom in for specific details. PiccyBot answers any image-related query with a clear calm voice. It is available in the Apple App Store now: https://apps.apple.com/us/app/piccybot/id6476859317 App info is currently processing and/or the app is not yet fully available for sale on the US App Store.
I have updated the app to make it fully voice over accessible for blind and low vision users. I have also added extra models. You now have a choice between GPT4, Google Gemni and Claude 3 to process the images. Each of these models has their own advantages. Which vision model do you prefer, currently?
