What is OCR?
OCR (Optical Character Recognition) converts images of text — scanned pages, photos, screenshots — into machine-readable text. This page performs OCR locally in your browser using Tesseract.js and pdf.js. No upload is necessary; files stay on your device.
Use cases
- Convert scanned invoices, receipts, and reports into searchable text.
- Extract text for translation, editing, or archiving.
- Convert documents into DOCX / HTML / plain text for editing.
Supported image formats — short guide
HEIC / HEIF — modern iPhone image container (High Efficiency). Browser decode may require heic2any; encoding HEIC in-browser is usually unsupported. This tool decodes HEIC to JPEG for processing.
AVIF — modern image format with excellent compression; encoding support in browsers is growing but limited. Use when supported.
WEBP — widely supported modern format with good compression for photos and graphics.
SVG — vector format. This app rasterizes SVG to PNG when embedding into PDFs or OCR (text inside SVG that is actual text may require different handling).
TIFF — common for scanned images. Multi-page TIFFs are not fully supported client-side; server-side tools are recommended for complex TIFFs.
PNG / BMP / JPEG — standard raster images. PNG supports transparency; JPEG is lossy and good for photos; BMP is uncompressed and large.
How to use OCR (step-by-step)
- Select the tool at the top (PDF→OCR, IMG→OCR, etc.).
- Drag & drop or click to choose your file(s).
- For PDFs: use the Pages field to process only desired pages (example:
1-3,6).
- Choose the language from the dropdown. Use "Auto" or "Mixed – Major" for mixed-language documents. If unsure, let the tool suggest a language from the first page/image (it will show a badge).
- Optional: enable Preprocess (binarize) to improve OCR on low-contrast or noisy scans.
- For PDFs: Prefer selectable text — the tool will automatically try to extract text without OCR (faster & more accurate). If no selectable text, OCR will run on rendered images.
- Click Run / Create → wait for progress; downloads will appear in the Outputs area and Preview Dock.
Card-specific quick help
- PDF → DOCX (OCR) — Consolidated .docx output. Uses selectable text when available; otherwise OCR. Use the Pages box and Preprocess toggle.
- PDF → OCR — Multi-output OCR: TXT, HTML, DOCX, ZIP. Good when you want per-page text files and multiple formats.
- IMG → OCR — OCR for individual images or batches. Use language and preprocess options. Best for scanned photos of documents.
- PDF → IMG — Export individual PDF pages as images. Choose format (PNG/JPEG/WEBP/AVIF/SVG), pages, and ZIP when multiple.
- IMG → PDF — Combine multiple images into a single PDF with each image as a page.
- IMG → IMG — Convert image formats (e.g., PNG → WEBP). Use ZIP for batch downloads.
- Compress — Compress PDFs by re-rendering pages to compressed JPEGs inside a PDF, or compress images to WEBP. Preview compare is provided.
Support: skycommunics@gmail.com