logo
episode-header-image
Jun 2025
9m 32s

Transform PDFs with AI-Powered OCR: Your...

AppleVis Podcast
About this episode

In this episode, Gaurav offers a hands-on walkthrough of PDFgear: PDF Editor & Reader for Mac OS — a free PDF reader available on the Mac App Store — spotlighting its AI-powered OCR (Optical Character Recognition) capabilities. This feature is especially handy for transforming PDFs composed mainly of images into editable, searchable text. The demo is performed on an M1 MacBook Air running the latest Mac OS Sonoma.

Key Highlights:

  • About PDFgear:

    • A free PDF reader app available on the Mac App Store.
    • Stands out with its AI-driven OCR functionality.
  • Demo Setup:

    • Conducted on a MacBook Air with Mac OS Sonoma.
    • Uses a PDF titled Malaysia Wildlife Document, mostly image-based.
  • Step-by-Step Walkthrough:

    • Opening the PDF: Launch the document in PDFgear via the ‘Open with PDF Gear’ option.
    • Navigating the App: Use VoiceOver (VO) commands to explore the window spots menu and locate pages heavy with images.
    • Running OCR: With VO, select the OCR button and choose ‘Current file OCR’ to begin processing. The OCR completes quickly — about 15 to 20 seconds for 134 pages.
    • Exporting Text: Export options include ‘Export to one file’ or ‘Export to separated files.’ Due to accessibility challenges with the save dialog, it’s best to stick with default directories.
    • Accessing Converted Text: Find the output text file in the ‘Downloads’ folder and open it with TextEdit to review the OCR results.

This detailed guide empowers listeners to easily convert image-based PDFs into accessible, searchable text, improving document usability across devices.

Try PDFgear on the Mac App Store:https://apps.apple.com/us/app/pdfgear-pdf-editor-reader/id6469021132?mt=12

Transcript

Disclaimer: This transcript was generated by AI Note Taker – VoicePen, an AI-powered transcription app. It is not edited or formatted, and it may not accurately capture the speakers’ names, voices, or content.

Gaurav: Okay, guys, so today I'm doing a brief audio demonstration on the PDF gear application. This is a free PDF reader on the Mac App Store, and its unique point is that it can use AI to convert or to OCR documents. So that basically means if you have a document, a PDF document, which is mainly in the form of images, you can use the AI-powered features in this application to convert it into text, which you can then read. So I'm going to demonstrate that feature for you today. I'm using M1-powered MacBook Air using the latest version of Mac OS Sonoma. I'm going to navigate to a PDF document on my Mac, which was sent to me by someone called the Malaysia Wildlife Document.

Gaurav/VoiceOver: I'm going to V-O-Shift-M to open the context menu. Open with. Open with. Steam app. PDF expert app. PDF gear app.

Gaurav: So I'm going to open with PDF gear.

VoiceOver: With PDF gear. Malaysia wildlife. PDF window.

Gaurav…

Up next
Oct 28
iPhone Air: Unboxing and First Impressions
In this episode, David Nason unboxes an iPhone Air and gives his first impressions of the device. Apple’s thinnest phone to date, the iPhone Air was released alongside the iPhone 17, 17 Pro and 17 Pro Max in September 2025. Our thanks to Apple for providing this device for review ... Show More
10m 15s
Oct 27
How to Opt Out of Offers and Promotions in the Wallet App on iOS
In this episode, Tyler demonstrates how to opt out of notifications for offers and promotions in the Wallet app on iOS.The Wallet app, responsible for managing payments, orders, passes, and more, often sends important notifications related to users' financial activity. However, n ... Show More
3m 6s
Oct 12
Bridging Access to Braille: An In-Depth Look at Braille Access on iOS 26
In this episode, Scott Davert gives us an in-depth demonstration of Braille Access. New in iOS 26, Braille Access aims to offer an experience similar to dedicated braille note takers.TranscriptDisclaimer: This transcript was generated by AI Note Taker – VoicePen, an AI-powered tr ... Show More
48m 9s
Recommended Episodes
Apr 2017
Feature Processing for Text Analytics
It seems like every day there's more and more machine learning problems that involve learning on text data, but text itself makes for fairly lousy inputs to machine learning algorithms.  That's why there are text vectorization algorithms, which re-format text data so it's ready f ... Show More
17m 28s
Jul 2024
755: 700 MB of GIFs
David is launching a scholarship program with the Productivity Field Guide, Stephen bought a new e-reader, and they both have spent some time in their Inboxes to bring feedback to the show this week. 
1h 12m
Oct 2016
171: ‘Prisoner’s Dilemma Multitasking’ With John Moltz
Special guest John Moltz returns to the show. Topics include what we expect from this week's Apple Event for new Mac hardware, and my impressions of the Google Pixel phone after a week using one. 
2h 6m
Jul 2018
Switched from iPhone to Android, Can't Get Texts
From the mailbag: Faby writes in and says she switched from an iPhone to a Samsung Galaxy S9+ and now her text messages aren't coming through. Here's the fix.Deregister and Turn off iMessage:<a href="https://selfsolve.apple.com/deregister-imessageEmail" target="_blank" rel="noref ... Show More
4m 42s
Sep 2017
What happens when you close the lid on your laptop?
<p>Do you know what your laptop does when you close the lid without powering it down first? Does it shut it off, or put it to Sleep mode, or Hibernate, or maybe it does nothing at all?   It’s interesting to find out what people think about this process. Some people assume that wh ... Show More
8m 50s
May 2024
The persuasive power of profanity
Warning. This episode contains explicit language.  In 2018, KFC told the world they FCK’d up. Today on Nudge, Professor Moore shares the science behind swearing and reveals if swearing in ads helps or hinders a brand. Access the bonus episode here: https://nudge.ck.page/e1bed9b ... Show More
25m 27s
Dec 2022
258: A Less-Cloudy Outlook
Abandoning the CloudKit plan for Overcast in light of new information. 
29m 28s
Jan 2015
107: ‘Now It’s All Floppy’ With Guest Marco Arment
Special guest Marco Arment returns to the show. Topics include microphones; Marco’s much-publicized article last week on Apple’s seemingly declining software quality; talking to the press and agreeing to interviews; Apple’s relatively tiny developer relations team (and how that p ... Show More
3h 4m
Jul 2025
Ep. 362: The Texting Dilemma
<p>When we think about unhealthy phone usage, we think about the flashing apps, like TikTok and Instagram, in which billions of dollars have been spent to grab our attention. In this episode, Cal points to an unassuming culprit that may be just as responsible: simple messaging ap ... Show More
1h 10m
Nov 2022
Episode 119 - Reading Alexa's Signature
<p>Not every technology we deal with in Voice is a #VoiceFirst technology, sometimes we need some "adjacent" skill. This week, Mark discusses some recent issues he had involving the validation signature that Alexa provides to skills that run outside AWS Lambda, and Allen provides ... Show More
22m 1s