MarkPrep

Image to Markdown

Extract text from images to Markdown with local OCR — nothing uploaded.

Drop files, paste, or click to browse
PDF, Word, Excel, PowerPoint, HTML, CSV, JSON, EPUB, images and more. Nothing is uploaded.
Network requests that left this page during conversion: 0We're not asking you to trust a privacy policy. Press F12 → Network and watch.

MarkPrep runs Tesseract OCR in your browser to pull text out of PNG, JPG and WEBP images. The engine, the model and the WASM all load from our own servers as static assets, then everything runs locally — no OCR API, no page cap. Images are upscaled, grayscaled and binarised first to lift accuracy, and low-confidence results are flagged in the Verify tab.

How to convert image to markdown

  1. 1Drop your image onto the box above, or click to browse. Nothing uploads — the file is read in your browser.
  2. 2MarkPrep converts it to Markdown locally and shows a live token count for your chosen model.
  3. 3Check the Preview, adjust the chunk size, and review the Verify tab for anything worth a second look.
  4. 4Copy the Markdown, download the .md/.zip, or export JSONL chunks for your RAG pipeline.

Format notes & gotchas

  • Clear, printed text works best. Handwriting and low-resolution phone photos are hard for any local OCR.
  • The first OCR run initialises the language model (self-hosted) — subsequent runs are faster.
  • For frontier accuracy on hard scans, Pro offers bring-your-own-key OCR to your own provider.

Related converters

Scanned PDF to MarkdownPDF to MarkdownWord to MarkdownHTML to MarkdownRead the guide

Frequently asked questions

Does the image get uploaded for OCR?+

No. Tesseract runs in your browser via WebAssembly. The image never leaves the tab. Bring-your-own-key OCR (Pro) is the one optional path where a page goes to your own AI provider with your own key.

Is my file uploaded anywhere?+

No. Conversion runs entirely in your browser tab using WebAssembly. There is no upload endpoint — open your browser's Network tab and watch: nothing leaves the page. The only labelled exceptions are fetching a public URL and optional bring-your-own-key OCR.

How much does it cost?+

Conversion and the entire AI-Ready Pack — token counts, chunking, JSONL export — are free and unlimited, because they run on your hardware. Pro ($4/mo) adds workflow features like the local MCP server, watch folders and saved profiles.

Are the token counts accurate?+

Exact for OpenAI models (GPT-4o, o-series) via their published tokenizer. For Claude and Gemini we show a labelled approximation, because those tokenizers aren't public.

Want it inside your workflow?

Conversion is free forever. Pro ($4/mo) adds the local MCP server so Claude Code converts files on your machine, plus watch folders, saved profiles and encrypted sync.

See pricing