cuuupid/markitdown 🖼️📝 → 🖼️

▶️ 72.3K runs 📅 Dec 2024 ⚙️ Cog 0.13.6 🔗 GitHub ⚖️ License
ocr pdf-to-markdown speech-to-text

About

Microsoft's tool to convert Office documents, PDFs, images, audio, and more to LLM-ready markdown.

Example Output

Output

Example output

Performance Metrics

4.13s Prediction Time
4.15s Total Time
Input Parameters
doc (required) Type: string
Supports PDF, PPTX, DOCX, XLSX, PNG, JPG, MP3, WAV, HTML, CSV, JSON, XML, and more.
openai_api_key Type: string
(Optional) OpenAI API key
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
/tmp/tmp65nbl8y2Tradewinds Marketplace Announcement Revision 6.pdf
<markitdown._markitdown.DocumentConverterResult object at 0x7c1288215090>
Version Details
Version ID
dbaed480930eebcf09fbfeac1050a58af8600088058b5124a10988d1ff3432fd
Version Created
January 17, 2025
Run on Replicate →