Hi All,
I've just released VOCR 2.0, packed with many new features compared to version 1.0. Please check out the demo and download it here: https://chigkim.github.io/VOCR/
If you're not familiar with the app, here's a brief description:
"Discover the cutting-edge capabilities of VOCR, your ultimate OCR and AI-powered screen recognition tool designed to enhance your digital accessibility experience. Beyond the simple navigation feature with OCR, VOCR seamlessly integrates with VoiceOver, enabling users to effortlessly capture and recognize screen content with intuitive and customizable shortcuts. With features like Real-Time OCR, users can continuously monitor and read live content, such as subtitles. The ASK AI functionality allows you to leverage advanced AI models, including OpenAI GPT to ask detailed questions about images and receive insightful answers. It also supports local vision language models via Ollama for your privacy. Explore with AI takes it a step further by analyzing images, identifying different areas, and providing comprehensive descriptions."
Here are the new features:
* Ask AI (OpenAI GPT-4, Ollama)
* Explore with AI (OpenAI GPT-4 Only)
* Capture image with a camera and ask AI: Command+Shift+Control+C
* Supports FaceTime, external, and iPhone cameras (with Continuity Camera feature)
* Open image files from Finder
* VOCR Menu: Command+Shift+Control+S
* Real-time OCR: Command+Shift+Control+R
* Object detection for icons
* Auto Scan
* Customize shortcuts
* Auto updates
* Save last image
* Save OCR results
* Faster VOCursor scanning
* Target window feature
* Disable mouse movement
* Launch on login
* Startup sound
* Logger
Enjoy!
Comments
Great, downloading it now…
Great, downloading it now. Been on the beta already so not expecting many changes?
You're my hero!
This is such a wonderful app. Great work!!
Best
M
Thanks for this app
Just updated from the alpha which already had the update feature. Even as a dev the psychological satisfaction of not having to manually download, remove the older one and reinstall is just so cool
This is the only reason I…
This is the only reason I stay on mac. It is the most useful app out there.
I was speaking to apple accessibility support yesterday and he mentioned he had heard of it too so it would seem people are talking about it. I really do hope apple comes along and gives you a bunch of money. You're doing their job for them.
Please forgive my ignorance
I am sure there are a variety of situations where this app would be very helpful, but since I have no iddea what those situations might be, would someone mind describing a few?
Thank you,
Bruce
I use it for Bambu Studio…
I use it for Bambu Studio which is a 3D printer application for my printers. The accessibility is poor so I use this to navigate, change print settings, start prints etc.
I also use it on some badly designed websites.
I use it for the raspberry pi imager for mac which is still inaccessible.
Basically, it's very good for those fringe apps that maybe not all of us use and therefore don't develop their accessibility.
Request to add support for Chinese.
Dear Developer,
Thank you very much for developing the VOCR application. Many visually impaired users from China are eager to use this application as well. Could you please consider adding support for Chinese? The image recognition API in macOS now supports Chinese. We hope that future updates will include support for more languages, including Chinese. Thank you.
Chinese Support
The interface is in English, but I already enabled language detection for OCR, so it should be able to recognize Chinese.
Also, if you use OpenAI GPT model, I believe it can generate image description in Chinese. Just ask the question in Chinese.
Not working on iMac 2023 with M3 chip
Hello,
first of all, thank you very much for this really useful app. However, when I shared this app with other users in my country, one user reported he is unable to launch VOCR successfully on one of his Macs. Specifically, the Mac in the question is an iMac 2023 with the M3 chip and macOS Sonoma 14.5. He said that after trying to launch the VOCR app from the Applications folder and allowing it as an app downloaded from the Internet, VOCR does not appear among the menubar status icons.
Any ideas what might be going wrong here?
Immense Chi Kim, an infinite thank you!
I am a very happy user of VOCR already from the version for MacOS Catalina., but surely with the 2.0 dearWho Chi Kim you gave us a great leap in quality, Apple should hire you immediately! I am also writing to ask you for clarification. When I make an OCR with the "Target Window" option enabled, in the result of the OCR I also find the displayed dialogue from which I selected which window to recognize. Is it inevitable, or does it only happen to me for some reason unknown to me? Thank you and congratulations again!
Bruce
I use it to play Playstation games mainly navigate menues and such not actual game play.
Is this just AI now?
So if I Ctrl+Cmd+Shift+W it now seems to be requiring AI. I've seen the options to change engines etc. But in the old version of VOCR, it just used OCR. Is this no longer an option or am I doing something wrong?