Tools

Baidu PaddlePaddle's official OCR and document parsing tool: the paddleocr command reads text from images and parses PDFs and scans into Markdown or JSON, supporting 100+ languages with models that run locally.

Official PaddleOCR MCP: text recognition and layout parsing for images and PDFs (PP-OCR, PP-StructureV3, PaddleOCR-VL), returning text or Markdown. Runs inference locally, or calls the official API or a self-hosted service.

Document parser from OpenDataLab that turns PDFs, images and Office files into Markdown or JSON, handling tables, formulas and complex layouts well, with page-by-page reading and citation anchors for agents. Parses locally by default; needs Python 3.10+.

Classic open-source OCR engine and CLI that reads text from images and outputs plain text, hOCR, searchable PDF or TSV. Supports 100+ languages; install the language data for each language you need.

Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.

Converts PDFs, images, PPTX, DOCX, XLSX, EPUB and more into Markdown, JSON or HTML, preserving tables, formulas and layout, with optional LLM help for higher accuracy. Needs Python 3.10+ and PyTorch; large-scale commercial use of the model weights needs a paid license.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Batch-translates text in manga, posters and screenshots with one command: detects text, runs OCR, erases the original and typesets the translation back into the image. Japanese-focused, with 20+ languages supported. Install from source (Python 3.10+); offline models, DeepL or LLM APIs.

Extracts subtitles burned into videos to SRT or TXT, with all OCR done locally in 87 languages. Mainly a GUI (with batch mode); the CLI backend/main.py reads the video path and subtitle area from stdin. Needs Python 3.12+ and PaddlePaddle; paths cannot contain spaces or Chinese characters.

Local image processing MCP: crop, resize, rotate, add text and watermarks, blur, remove backgrounds, detect objects and extract text with OCR, with no images uploaded anywhere; handy for photos, scans and course visuals. Needs Python 3.10 and pipx; first install downloads detection models.

MinerU's official MCP: parses PDF, Word, PowerPoint and images into Markdown via the mineru.net cloud API, keeping tables and formulas. The keyless Flash mode works out of the box; add a token for higher quotas and more formats.