Free online PDF and document tools

Runs DeepSeek-OCR 2 on document images.

Detects and reads text in images using OnnxTR.

PaddleOCR v6 text detection and recognition running on ONNX Runtime CPU.

Reads text from an image and translates it.

Convert documents to Markdown or JSON with metadata using Docling.

Extracts Persian text from images.

Interactive demo of the DeepSeek-OCR model for reading text from images.

Convert PDFs and other documents to Markdown using the Docling library.

Chat with documents or websites using a small Gemma 3 1B model.

Turns scanned pages into markdown with a 3B OCR model.

Uploads a PDF and returns a short summary.

Recognizes Japanese text in manga panels.

Tiny ONNX OCR model that converts PDFs and images into markdown.

Finds and redacts personal data in PDFs, images, Word files and spreadsheets using OCR and entity detection.

Arabic OCR that preserves tashkeel diacritics.

Detects the layout of a document page with the DocLayout-YOLO model.

Reads document images and PDFs and streams back their content as structured Markdown text.

Extracts text from PDFs and images with Tesseract.js; the page says files stay in your browser.

Converts a PDF or text into a podcast, lecture or summary read aloud, using your OpenAI key for scripting and voices.

Demo of PDFMathTranslate, which translates PDF documents including their mathematical content.