OCR — Image & PDF to Text
Pull selectable text out of photos and scanned PDFs — 100% on your device.
Scan and extract text from an image or PDF with OCR, then copy it out. Free, supports 100+ languages, and runs in your browser — nothing is uploaded.
About OCR — Image & PDF to Text
OCR (Image & PDF to Text) is a free, in-browser tool that extracts selectable, editable text from photos, screenshots, and scanned PDFs using the Tesseract optical-character-recognition engine. It runs entirely on your device with no signup — your image or PDF is never uploaded; only the OCR engine and language model download once from a CDN. For PDFs it reads any real embedded text layer instantly and only OCRs the pages that are image-only scans.
How to use OCR — Image & PDF to Text
- Pick the document language: English (default), Spanish, French, or German. Extra models download once on first use, so match the language to your file for the best accuracy.
- Drop an image (PNG, JPG, WebP, GIF, BMP, or TIFF) or a PDF onto the drop zone, or click to browse. Files up to 50 MB are accepted.
- Wait while the text is extracted on your device — PDFs reuse any embedded text layer instantly and OCR runs a few seconds per scanned page (slower on mobile).
- Review the recognized text and the stats: total pages, the OCR-vs-embedded split, average OCR confidence, and character count.
- Edit the text directly in the box to fix any recognition errors, then Copy it or download it as a .txt file.
Frequently asked questions
- Are my files uploaded to a server?
- No. The image or PDF is read and processed entirely in your browser and is never uploaded. The only network request is a one-time download of the Tesseract OCR engine and the selected language model from a pinned CDN.
- Is it free and do I need an account?
- Yes, it is completely free with no signup or account. Everything runs client-side in your browser.
- Which file formats can it read?
- Images in PNG, JPG, WebP, GIF, BMP, and TIFF, plus PDF files. The maximum file size is 50 MB, and PDFs are processed up to the first 100 pages.
- Does it work on scanned PDFs and regular PDFs?
- Both. For each PDF page it first checks for a real embedded text layer and uses it directly when present (instant and exact). Pages that are image-only scans are rasterized and run through OCR, and the summary shows how many pages used each path.
- What languages are supported?
- English, Spanish, French, and German. English is the default; the other language models download from the CDN the first time you select them. Choosing the language that matches your document improves accuracy.
- How accurate is the text and what affects it?
- OCR on a clean, high-contrast, upright scan is usually very good, and the tool shows an average confidence score. Accuracy drops on blurry, low-resolution, skewed, or hand-written text; if confidence falls below 60% it warns you, and a sharper scan or the correct language setting usually helps.
People also search for
OCR — Image & PDF to Text is also known as ocr to text, image to text, pdf to text, ocr converter, ocr text scanner, how to ocr a pdf, extract text from image.