Text in images should be easy to copy
Image to Text App is a free image to text converter that runs in your browser. Paste a screenshot or drop a photo, scan or PDF, and get text you can edit, check and export, without signing up and without uploading your images.
At a glance
- languages, several on one page
- 47
- images in one batch
- 50
- download formats
- 9
- accounts needed
- 0
Why we built it
Most of the text people need is already in front of them: an error message, a receipt, a slide, a page of notes. Getting it out should take seconds. Too often it means uploading a private image to a server you know nothing about, sitting through ads or running into a daily limit.
So we built the opposite. Image to Text App reads the image where it already is, on your device, with the open-source Tesseract engine. There is no account to create and nothing to install, and once the engine has loaded it keeps working offline.
What we care about
-
Private by design
Images are read in your browser, not on our servers. History is off unless you turn it on, and there is no tracking or advertising.
-
Free, with no catch
No sign-up, no ads, no captcha and no daily limit for reading on your device. Up to 50 images at a time, 25 MB each.
-
Honest about limits
OCR makes mistakes, so the tool shows you where. Words it was unsure about are underlined and the confidence level is shown, never a promise of perfection.
-
Made for real documents
Tables become editable grids, receipts become fields, code keeps its indentation and documents keep their headings and lists.
How it works
- Add an image. Paste, drop, pick a file, take a photo or paste a link. JPG, PNG, WebP, HEIC, TIFF, GIF, BMP and PDF all work.
- It is read on your device. Auto improve cleans up the image, the type of page is detected, and Tesseract reads the text right in your browser.
- Check, edit and export. Fix any underlined words, then copy the text or download it as Word, Excel, PDF, Markdown, JSON and more.
Want the details? Read how OCR works, or see what happens to your images.
Built on open source
The tool stands on the work of these open-source projects. Thank you to everyone who builds and maintains them.
- Tesseract Text recognition engine Apache-2.0
- Tesseract.js Tesseract in the browser Apache-2.0
- PDF.js Reading PDF files Apache-2.0
- libheif Opening iPhone HEIC photos LGPL-3.0
- CodeMirror Text editor MIT
- UTIF.js Reading TIFF images MIT
- fflate ZIP files MIT
- Svelte Workspace interface MIT
- Astro Website framework MIT
- Geist Typeface OFL-1.1
Questions, ideas or a file that won't read?
We'd like to hear from you.