Productive ToolboxImage to Text (OCR)
Extract text from photos, screenshots and scans with OCR in 23 languages, right in your browser.
Drop an image here, click to browse or paste a screenshot
JPG, PNG, WebP, HEIC, GIF, BMP, AVIF · the image is not uploaded
Next step
Related tools
Extract Text from Images with OCR
Optical character recognition (OCR) turns the letters in a picture into text you can copy, edit and search. Use it to grab a quote from a screenshot, copy the details from a photographed document, or digitise a printed page instead of retyping it.
This tool runs Tesseract, the widely used open-source OCR engine, inside your browser. It reads 23 languages, including accented European languages, Greek, Cyrillic, Arabic, Chinese, Japanese and Korean, and your image is never uploaded.
What to Expect from Different Images
| Image | Typical result | Why / tip |
|---|---|---|
| Screenshot of a web page or document | Excellent | Sharp, straight, high contrast |
| Flatbed scan at 300 dpi | Excellent | The resolution OCR engines are tuned for |
| Phone photo of a printed page | Good | Shoot straight on in even light, no shadows |
| Receipt or faded print | Fair | Low contrast; crop tightly around the text |
| Text on a busy photo, sign or product | Fair to poor | Crop to the text only |
| Handwriting | Poor | Printed-text engine; neat block letters work best |
How to Convert an Image to Text
- 1Add an image: Drop a photo, scan or screenshot (JPG, PNG, WebP, HEIC, GIF, BMP or AVIF) on the upload area, click to browse, or paste a screenshot with Ctrl+V (Cmd+V on a Mac).
- 2Choose the language: Pick the language of the text; it is preset from your browser language. Tick The text also contains English for mixed documents.
- 3Extract the text: Click Extract text. The first time you use a language, its data is downloaded once and then cached by your browser.
- 4Check and edit: Read through the result next to the image and correct any mistakes; a low confidence score means the image was hard to read.
- 5Copy or download: Click Copy text, or Download .txt to save it as a plain text file.
Frequently Asked Questions
Is my image uploaded to a server?
No. Text recognition runs in your browser with Tesseract, the open-source OCR engine, compiled to WebAssembly. The engine and the language data are downloaded from a public CDN the first time; your image itself never leaves your device.
How accurate is the OCR?
On clear printed text, such as a screenshot or a flat, well-lit scan, accuracy is usually above 95%. Blurry, skewed, low-resolution or low-contrast photos, decorative fonts and complex layouts give more errors, so always check the result.
Can it read handwriting?
Only neat, printed-style handwriting, and not reliably. Tesseract is trained on printed text; cursive handwriting usually needs a specialised handwriting recognition service.
How do I get the best results?
Photograph the page straight on in good light, fill the frame with the text, and avoid shadows and glare. Text should be at least about 20 pixels tall; crop away everything that is not text, and choose the right language.
Which languages are supported?
English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Swedish, Danish, Norwegian, Finnish, Czech, Romanian, Hungarian, Greek, Turkish, Russian, Ukrainian, Arabic, Chinese (Simplified), Japanese and Korean. Accents and special letters are recognised when the matching language is selected.
Can I extract text from a PDF?
If the PDF was made from a text document, open it in a PDF reader and copy the text directly. For a scanned PDF, save or screenshot the page as an image first, then add it here.
Does it keep the layout, tables and formatting?
No. The result is plain text with line and paragraph breaks. Columns are read one after another, and tables become lines of text, so tidy them up after copying.
Related Tools
Image Converter
Convert JPG, PNG, WebP and HEIC images between formats.
Image Cropper
Crop photos to any ratio or pixel size, rotate, circle crop.
Word Counter
Count words, characters, sentences, paragraphs, and reading time.
Remove Duplicate Lines
Deduplicate line-based text with case, whitespace, and sort controls.
Find and Replace
Search and replace text with regex, batch rules, and preview controls.
JPG to PDF Converter
Combine JPG, PNG, WebP and HEIC images into one PDF.
Image to Grayscale
Apply grayscale filter to images.
Image Compressor
Reduce JPG/PNG size in browser.
Image Resizer
Set custom width & height.
Base64 Image Encoder
Convert images to Base64 string.
Favicon Generator
Resize image to 16×16 or 32×32 for web.
Duotone Image Filter
Apply a two-colour gradient map to images for modern artistic effects.