Skip to content
Kordu Tools Kordu Tools

Image to Text (OCR)

AI Runs in browser

Extract text from images free online. AI-powered OCR supports 12 languages — copy or download extracted text instantly.

Last updated 01 Apr 2026

Upload any image and extract all text instantly using Tesseract.js — an AI-powered OCR engine running entirely in your browser. Supports 12 languages including English, Spanish, Chinese, Japanese, Korean, Arabic, and more. Colour-coded word confidence overlay shows recognition accuracy. Copy extracted text or download as a .txt file. Your images are never uploaded to any server.

Language data (2-15 MB) loads from CDN on first use and is cached automatically.

Click to upload or drag and drop

PNG, JPG, JPEG, WEBP, BMP, TIFF up to 50MB
Loading rating…

How to use

  1. 1

    Select your language

    Choose the language of the text in your image from the dropdown. English is pre-selected. Language data loads on first use and caches automatically.

  2. 2

    Upload your image

    Click the upload area or drag and drop a PNG, JPG, WebP, BMP, or TIFF image containing text.

  3. 3

    Wait for text extraction

    Tesseract.js analyses your image and extracts all visible text. This typically takes 2-10 seconds depending on image complexity.

  4. 4

    Review with word confidence overlay

    Toggle Show word regions to see colour-coded bounding boxes: green = high confidence, yellow = moderate, red = low. Review flagged words for accuracy.

  5. 5

    Copy or download

    Click Copy to Clipboard to copy the extracted text, or Download .txt to save it as a file.

Frequently asked questions

Is my image uploaded to a server?
No. All OCR processing runs in your browser using Tesseract.js and WebAssembly. Your images are never sent to any server.
Which languages are supported?
English, Spanish, French, German, Italian, Portuguese, Chinese (Simplified), Japanese, Korean, Arabic, Russian, and Hindi. Select your language before uploading for best results.
How accurate is the OCR?
Tesseract achieves high accuracy (95%+) on printed text in clear images with good contrast. Handwriting, decorative fonts, rotated text, or low-resolution images reduce accuracy. The word confidence overlay shows where the engine is uncertain.
What image types work best for OCR?
High contrast printed text on a clean background produces the best results — scanned documents, screenshots, receipts, and business cards. Images with complex backgrounds, small text, or heavy noise are harder to process.
What image formats are supported?
PNG, JPG/JPEG, WebP, BMP, and TIFF files up to 50MB.
What does the confidence overlay show?
Toggle Show word regions to display colour-coded bounding boxes around each recognized word. Green = high confidence (80%+), yellow = moderate (50-80%), red = low confidence (below 50%). Use this to spot words that may need manual correction.
Can I use OCR on handwritten text?
Tesseract was designed primarily for printed text. It can recognize some clear handwriting but accuracy is significantly lower than for printed fonts. For best handwriting results, use high-resolution images with clean letterforms.
Why is OCR slow for some images?
OCR processing time depends on image size, complexity, and number of words. Very large images above 3000px are automatically downscaled. Complex multi-column layouts or images with mixed languages take longer.
Can I extract text from a PDF?
This tool processes image files. To extract text from a PDF, use the PDF tools or first convert a PDF page to an image and then run OCR.

Optical Character Recognition (OCR) converts printed or handwritten text in images into

machine-readable text you can copy, search, and edit. Common uses include digitizing scanned

documents, extracting text from screenshots, reading receipts and invoices, converting

photographed notes into editable text, and pulling data from infographics.

This tool uses Tesseract.js — the JavaScript port of the Tesseract OCR engine originally

developed by HP Labs and maintained by Google. It runs entirely in your browser, so your

images are never sent to any server. Language data files (2-15MB each) load from a CDN on

first use and are cached for future sessions.

12 supported languages: English, Spanish, French, German, Italian, Portuguese, Chinese

(Simplified), Japanese, Korean, Arabic, Russian, and Hindi. Word confidence overlay shows

colour-coded bounding boxes: green (high confidence), yellow (moderate), red (low) — so

you can instantly see which words may need manual correction.

For best results, use clear images with good contrast between text and background. Printed

text in standard fonts at reasonable sizes achieves the highest accuracy. Very large images

above 3000px are automatically downscaled for speed. Output can be copied to clipboard or

downloaded as a .txt file.

Related tools

Image Compressor

Compress PNG, JPG, WebP, AVIF, GIF, BMP, ICO and more — reduce file size without losing visual clarity.

EXIF Remover

Strip EXIF, GPS, and all metadata from photos before sharing — protects your location and privacy.

AI Image Caption & Alt Text Generator

Generate descriptive captions and accessibility alt text for images using AI — free, no account, runs in your browser.

Base64 Encoder/Decoder

Encode text or files to Base64 or decode Base64 strings back to plain text — real-time, fully in your browser.