Extract text from an image
Pull every readable word out of a picture and copy it. The image stays on your device the whole time.
- Nothing is uploaded
- Works offline after first use
- Open source
- No watermark · limit is your device’s memory; phones hold less
Extract the text from any image in your browser: photos, screenshots, scans. It is free, needs no account and adds no watermark, and your files are not uploaded: everything runs in your browser on your device. The first run downloads the text reader (about 4 MB) and the WebAssembly engine that runs it to your browser, and after that the tool works offline.
Done
Free, no ads. Support StayPut
Open the network tab. Your files never appear in it.
Add files and run the tool to see every request this tab makes.
Your files are processed on this device and never sent to a server. Reload the page to clear everything from memory.
Retyping text from a picture is slow and error-prone: a long quote in a screenshot, a table in a photo of a handout, the small print on a label, a serial number on the back of a router. Optical character recognition (OCR) does it in seconds. Drop the image, press Read text, and the words appear in a box you can copy from or save as a plain text file.
Most online extractors send the picture to a server to read it. That is a poor trade when the image is a payslip, a medical letter or a chat you screenshotted. Here the recognition runs in your browser tab with Tesseract, the long-standing open-source OCR engine, so there is no upload, no account and no daily limit.
Drop a batch and every image is read in turn, each with its own copy button and .txt file. Choose Join into paragraphs when the text is going into a document, so lines that wrapped in the image flow together again.
Pulling one short value out of an image, like a serial number, a Wi-Fi password, a tracking code or an IBAN, is where OCR mistakes cost the most. Letters and digits that look alike get swapped: O and 0, l, I and 1, S and 5, B and 8. The reader has no way to know which a code meant. Compare anything you will type into a form against the image before you rely on it.
Join into paragraphs does more than remove line breaks. Blank lines in the image stay as paragraph breaks, and a word hyphenated across the end of a line is put back together, so “infor-” and “mation” become “information”. Use it for articles, letters and book pages. Keep line breaks as they are for addresses, receipts and anything laid out line by line.
How it works
- Drop one or more images, or tap to pick them. Photos, screenshots and scans all work.
- Keep line breaks for lists, tables and code; join them into paragraphs for running text.
- Read text, then copy the result or save it as a .txt file.
In your browser, not on a server
Your browser decodes the image (libheif or the Squoosh decoders step in for HEIC, AVIF and JPEG XL), enlarges small screenshots so letters are big enough to read, and hands the pixels to Tesseract, the open-source OCR engine first built at HP and later developed by Google, compiled to WebAssembly by tesseract.js (Apache-2.0). Its neural network model for English is served by this site and loaded the first time you run it. The text is recognised line by line inside a worker in your tab.
Compared with upload-based tools: The pictures people want text from are often private: a letter, a receipt, a bank statement, a prescription, a screenshot of a conversation. Online OCR sites upload the image to their server to read it and keep it for hours, and several limit free use or ask for an account. Here the image never leaves your device, and after your first run the page keeps working with Wi-Fi off.
Verify it yourself. Give the page a short while after your first run to save itself for offline use, then turn off Wi-Fi or switch to airplane mode and run the tool again. Or open your browser's developer tools (F12, or Cmd-Option-I on a Mac), pick the Network tab, and watch it while you convert. The panel above does the same count for you.
Questions
Can it extract text from a table?
It reads the words row by row, left to right, with spacing between columns collapsed. The numbers and labels come out correctly, but you will need to paste them into a spreadsheet and split the columns yourself.
Does it keep bold, fonts or layout?
No, the output is plain text. That is usually what you want for pasting, searching or quoting. If you need a formatted document from a PDF with selectable text, PDF to Word keeps headings and paragraphs.
Why did it read a 0 as the letter O?
The two look almost the same in many fonts, and in a code there are no surrounding words to tell the reader which one makes sense. The same goes for 1, l and I, or 5 and S. For serial numbers, passwords and account numbers, check each character against the image.
Can I extract text from a scanned PDF?
Not directly; this page reads images. Turn the pages into images with PDF to Image, then drop them here and each page is read in turn. If the PDF already has selectable text, you do not need OCR at all: copy it from a PDF reader, or use PDF to Word to keep the layout.
Is the file uploaded anywhere?
No. There is no server in this process. The page is a static file and the work is done by code running inside your browser tab. Give the page a short while after your first run to save itself for offline use; then you can turn off Wi-Fi and it still works.
More image tools
Image to text
Get the words out of a photo, screenshot or scanned page, ready to copy. The image is read on this device and never uploaded.
AI image upscaler
Make a small picture bigger and sharper with a neural network that runs on this device.
Remove object from photo
Paint over what should not be there and let a small AI fill it in, on this device.
Adjust photo
Brightness, contrast, saturation, warmth, sharpening and invert, previewed live and made on this device.
Other conversions
Guides
- How to copy text from an imageiPhone, Android, Windows and Mac can all turn a photo of text into text you can select and paste. Here is how on each.
- A free TinyWow alternative that never uploads your filesTinyWow puts a lot of tools in one place, but your files go to it first. Here is what changes when they never leave your device.