How to extract text from image files, without uploading them
Search how to extract text from image files and the answer you are given is a website: paste the picture in, get the words out. It works. It is also, for most people asking, the worst of the available options — because three tools you already own do the same job, and one of them does it without the file leaving your computer.
“All text recognition processes are performed locally on your device.”
Microsoft, on the Snipping Tool’s text feature, read 22 August 2026. That single sentence is the
reason to start with the tools you already have. Every converter website works the other way
round: you hand it the document first and read the small print afterwards — and the images people
need text out of are usually invoices, letters, contracts and forms, which is to say exactly the
documents you would not post to a stranger.
The technology has a name — optical character recognition, OCR — and it stopped being specialist software some years ago. Windows ships it in the screenshot tool. Apple ships it in Photos and in the camera itself. Google runs it on anything you drop into Drive. None of these is a download, a trial, or a signup.
Windows — Snipping Tool
already installed · runs on the device
Capture the image, then select the Text actions button. Microsoft’s description: it
“activates the Optical Character Recognition (OCR) feature… you have the option to either select
and copy specific text or use the tools to Copy all text or to Quick redact any email
addresses or phone numbers in the snip”.
Quick redact is the part worth remembering. It blanks addresses and phone numbers before
you send the screenshot on — the opposite job, and one people usually do by hand and badly.
iPhone and iPad — Live Text
built in · iOS 15 or later
Open the photo, touch and hold a word, drag the grab points, then tap Copy — or tap Select
All for the lot. It works in the Camera app too, so you can lift text off a page without taking a
photo at all.
If nothing happens, the switch is at Settings › General › Language & Region › Live
Text. Apple’s requirement is an iPhone XS or XR or later; text in video needs iOS 16
or later.
Anything else — Google Drive
free · the file is uploaded
Put the file in Drive, right-click it, then Open with › Google Docs. It handles multi-page
PDFs, which the other two do not, and Google says Drive detects the document’s language itself.
The trade is plain: this one does send your document to a server. For a scanned book
chapter that is nothing; for a payslip it is a decision.
Which one to reach for is decided by two questions, and neither of them is about accuracy — all three are good now. The first is whether the thing is on your screen or in your hand: if you can see it, the screenshot route is fastest. The second is whether the document is yours to share. That is what separates the local tools from the Drive route, and it is the question the converter sites never put to you.
What Google says will and will not survive
Quoted from Drive’s own documentation, because it is more honest than anything a
converter site will tell you.
Kept
“Bold, italics, font size, font type, and line breaks are likely to be retained.”
Lost
“Lists, tables, columns, footnotes, and endnotes are not likely to be detected.” If your image is a table, expect to rebuild it.
File size
“The file should be 2 MB or smaller.”
Text height
“Text should be at least 10 pixels high.” Small print in a wide photo often is not.
Orientation
“Documents must be right-side up.” Rotate before uploading, not after.
Typeface
“Use common fonts, such as Arial or Times New Roman.” Handwriting and display faces are where these tools fail.
The limits above are not Google being modest. They describe how OCR works everywhere, including in the paid tools. Recognition reads shapes in a line; it does not understand that four columns are four columns. So a page of running prose comes back almost perfect, and a table comes back as a stream of numbers in the wrong order. If your image is a table, the extraction is the easy half and the rebuilding is the work.
Always read the result against the original. OCR does not fail loudly. It substitutes: a 1 for an l, a 0 for an O, rn for m. The output looks clean and reads clean, and the error sits inside an account number where nothing about it looks wrong. Anywhere the text is a figure rather than a sentence — an amount, a reference, a date — check it by eye before you rely on it.
Every quoted line on this page comes from Microsoft’s, Apple’s and Google’s own documentation, read on 22 August 2026 and listed below. The argument for starting with what you already own, and the warning about silent substitutions, are ours.
Cropping and straighteningOrientation is one of Google’s six requirements, and the easiest to fix.Being built
Compressing imagesThe 2 MB limit, and how to meet it without losing the text height.Being built
Converting formatsWhich formats these tools accept, and which they quietly refuse.Being built
What this tower will not do
It will not send you to a converter site first. Three tools you already own do this, and one of them does it without the document going anywhere.
It will not claim OCR is solved. Tables, columns and handwriting still break it, and the documentation of the biggest provider says so in its own words.
And it will not skip the checking step. These tools substitute characters silently, which is fine in a paragraph and serious in an account number. What holds instead is simple: the capabilities, the settings and the limits on this page are quoted from Microsoft’s, Apple’s and Google’s own documentation, with the date each was read.
Where this page got its facts
Microsoft Support — Use Snipping Tool to capture screenshots, including Text actions, Copy all text, Quick redact and the note that recognition runs locally on the device — support.microsoft.com, read 22 August 2026.
Apple Support — Copy and translate text from photos on your iPhone or iPad, including the Live Text setting and the device and iOS requirements — support.apple.com, read 22 August 2026.
Google Drive Help — Convert PDF and photo files to text, including the file size, resolution, orientation and font requirements and what formatting survives — support.google.com, read 22 August 2026.
AG
Written by Alberto Gulotta
Founder and editor of AI Tools Primer, writing from Palermo, Italy. Thirty-five years of
taking computers apart, starting with a Commodore 64 — the long version is on the
about page.
No affiliate links and no paid placements anywhere on this site. Nobody pays to appear here,
and no company has seen this page before you did.
This is general information, not professional advice. Where a page touches money, health,
safety or the law, it names its source and the date it was read — and your situation may
still differ. See the privacy page and the
cookie policy.
