Image to Text
Get the words out of a photo, scan or screenshot, ready to copy.
Save your favourite tools
Create a free iBuildPDF account to keep your favourite tools and find them quickly anytime.
Free account. The PDF tools themselves never need one.
Select an image
or drag and drop here
Accepted formats: PNG, JPG, JPEG, WEBP, TIF, TIFF, BMP, GIF
Processing…
Quick facts
- What it does
- Reads the text in an image with OCR and gives it back as plain text you can copy or download.
- Input
- PNG, JPG, WEBP, TIF, TIFF, BMP or GIF
- Output
- TXT
- Processing
- On our server
- Files uploaded?
- Yes, temporarily
- Account required?
- No
- Best for
- Screenshots, photos of documents and notices, scanned pages and receipts.
- Main limitation
- Handwriting, very blurred photos and text on busy backgrounds are often misread. Layout, tables and formatting are not kept — use JPG to Word for a page you want to edit.
How to use this tool
- Choose a photo, scan or screenshot (JPG, PNG, WebP, TIFF, BMP or GIF).
- Leave the language on Detect automatically, or pick it, then press Apply. The image is sent over an encrypted connection.
- Wait while the text is read.
- Copy the text from the page, or download it as a .txt file.
Why use iBuildPDF
Text in a picture cannot be selected, searched or pasted: to a computer, a screenshot of an address or a photo of a page is only coloured dots. Retyping it is slow and brings in mistakes. Reading it with OCR gives you the words themselves, in seconds.
How it works
The image is turned upright, small screenshots are enlarged so their letters are big enough to read, and Tesseract, an open-source OCR engine, reads it on our own server. With Detect automatically, the script of the page (Latin, Arabic, Cyrillic, Chinese and others) is recognised first, and the language you browse this site in helps choose between languages that share a script. Line breaks follow the picture.
Frequently asked questions
Which languages can it read?
The languages installed on our OCR server, including English, Arabic, French, German, Spanish, Italian, Portuguese, Russian, Chinese, Japanese, Korean and Hindi. With Detect automatically the script is identified first; if the result looks wrong, pick the language from the list and run it again.
Can it read handwriting?
Neat printed handwriting sometimes comes through, but OCR is built for printed text and joined-up writing is usually misread. Check the result before you rely on it.
How do I get the best result?
Photograph the page straight on, in good light, with the text filling the frame, and keep it in focus. A screenshot is better than a photo of a screen. When a word comes out wrong, the picture usually shows why: a shadow, a fold or blur.
Can I convert several images at once?
One image per run. A multi-page TIFF is read page by page, up to 20 pages, and the text of each page is kept in order. For a stack of photos, JPG to PDF followed by OCR PDF keeps them together as one searchable document.
What happens to my image?
It is sent over an encrypted connection to our own OCR server, read, and deleted when the job finishes. The text is sent back to your browser only.