Zro7Zro7/Invoice Extractor

Invoice extraction

Pull invoice number, dates, subtotal, tax and total.

Runs entirely in your browser. Files never leave your device.
Runs entirely in your browser
OCR is powered by Tesseract.js compiled to WebAssembly. Language data (~10–15 MB per language) is fetched from a CDN the first time and cached — nothing is uploaded to any server.

Drop an invoice (PDF or image)

Single file

How it works

  1. 1

    Drop an image or PDF

    Add the file to recognize.

  2. 2

    Pick a language

    Choose the primary language for OCR.

  3. 3

    Copy or download text

    Grab the recognized text as plain text or structured data.

Frequently asked questions

Which languages are supported?

Tesseract.js ships language packs for 100+ languages, loaded on demand.

Is my scan uploaded?

No. Recognition runs in-browser via Tesseract compiled to WebAssembly.

How accurate is it?

Very good for clean scans and photos; noisy or low-DPI images benefit from cleanup and higher resolution.

Other tools to try

All OCR tools →

Image → Text

Extract text from any image — 19 languages supported.

PDF OCR

Recognize text in scanned PDFs, page by page.

Receipt Scanner

Grab merchant, date, items and total from a receipt photo.

Business Card Reader

Parse names, emails and phones — export as vCard.

Passport Mrz Reader

Read the MRZ zone from passports and ID cards.

Batch OCR

Recognize many images and download all text as a ZIP.

Explore more categories

PDFImageVideoAudioDatabaseArchive