Image to Markdown Converter

Upload a screenshot or photo of a document and get its content back as Markdown text. ParseJet OCRs the image and returns structured, editable text instead of pixels — free to try, no signup needed.

Drop a file here or browse

Accepts JPG,JPEG,PNG,GIF,WEBP,TIFF,BMP files

Free — 3 requests/day, no signup. for 300 credits/month free.

How it works

Upload your image

Drop a screenshot, scan, or photo above — JPG, PNG, WebP, GIF, TIFF, and BMP are supported.

OCR and structuring

ParseJet reads the text out of the image with AI vision and returns it as structured Markdown, not a flat character dump.

Copy your Markdown

Paste the result into notes, docs, or an LLM prompt — or call the API to process images in your pipeline.

Key features

What makes this image to markdown stand out.

AI vision OCR

Modern vision models read screenshots, scans, and photos — including imperfect lighting and skewed angles.

Structured output

The result is Markdown text in reading order — usable in docs and prompts, not a raw character dump.

All common image formats

JPG, PNG, WebP, GIF, TIFF, and BMP all work through the same tool and endpoint.

Screenshots of code and docs

Turn screenshots of documentation, error messages, and snippets back into editable, searchable text.

Multilingual recognition

Text in dozens of languages is recognized — not just English.

Batch API processing

OCR a folder of scans with a short script — one POST per image. See the Python example below.

Use cases

Common scenarios where this tool saves you time.

RAG and LLM pipelines

Images are invisible to text-based retrieval. Convert them to Markdown so screenshots and scans become searchable, promptable content.

Notes from whiteboards and slides

Photograph a whiteboard or projected slide and turn it into Markdown notes instead of retyping.

Scanned documents

Make scanned letters, forms, and printouts editable and searchable as structured text.

Recovering text from screenshots

That paragraph that only exists as a screenshot — get it back as real text you can quote and edit.

Automate with the API

Use the same tool programmatically. Works with any language — just HTTP.

cURL

# OCR an image into Markdown text
curl -X POST https://api.parsejet.com/v1/parse/auto/file \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]"

Python

import httpx
from pathlib import Path

# Batch-OCR a folder of scans to Markdown files
for img in Path("scans/").glob("*.png"):
    resp = httpx.post(
        "https://api.parsejet.com/v1/parse/auto/file",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
        files={"file": open(img, "rb")},
        timeout=120,
    )
    Path(img.stem + ".md").write_text(resp.json()["text"])

JavaScript

const formData = new FormData();
formData.append("file", imageFile); // PNG, JPG, WebP…

const res = await fetch("https://api.parsejet.com/v1/parse/auto/file", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY" },
  body: formData,
});
const { text } = await res.json(); // Markdown text

Want to automate this?

ParseJet API gives you the same parsing power via a single HTTP endpoint. No ffmpeg, no poppler, no tesseract — just one API call.

curl -X POST https://api.parsejet.com/v1/parse/auto/url \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com"}'

Read API Docs

Frequently asked questions

How do I convert an image to Markdown?

Upload the image above — ParseJet OCRs it with AI vision and returns the content as structured Markdown text. For automation, POST to /v1/parse/auto/file.

How is this different from plain OCR?

Plain OCR gives you a flat character dump. ParseJet returns the text as Markdown in reading order, so the result drops straight into notes, docs, and prompts.

What image formats are supported?

JPG, JPEG, PNG, GIF, WebP, TIFF, and BMP. For multi-page scanned PDFs, use our PDF to Markdown tool instead — it OCRs scanned pages automatically.

Does it work on photos, not just screenshots?

Yes — photos of documents, whiteboards, and printed pages work. Sharper, straighter, well-lit photos give the best results.

Does it read languages other than English?

Yes — text in dozens of languages is recognized, including CJK scripts and right-to-left languages.

Is it free?

Yes. You get 3 free conversions per day with no signup, and a free API account includes 300 credits per month. Paid plans start at $19/month.

Start extracting text for free

No signup required. Parse your first file in seconds.

View Pricing