PPTX to Text

Extract readable text from PowerPoint (.pptx) presentations using MinerU. MinerU outputs Markdown as the closest format to plain text.

Install

CODEBLOCK0

Quick Start

CODEBLOCK1

Authentication

No token needed for flash-extract. Token required for extract:

CODEBLOCK2

Create token at: https://mineru.net/apiManage/token

Capabilities

• - Supported input: .pptx (local file or URL)
• INLINECODE2: no token, Markdown output to stdout (max 10 MB / 20 pages)
• For truly plain text: use extract -f json and read text fields from JSON output
• Language hint with --language (default: ch, use en for English)
• Slide range with --pages (e.g. 1-5)

Notes

• - MinerU has no -f text format; Markdown output is the closest to plain text
• For .ppt (legacy format), use ppt-extract instead
• Output goes to stdout by default; use -o <dir> to save to a file or directory
• All progress/status messages go to stderr; document content goes to stdout
• MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU