Extract readable text from PowerPoint (.pptx) presentations using MinerU. MinerU outputs Markdown as the closest format to plain text.
npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
# Extract text from .pptx to stdout (no token required)
mineru-open-api flash-extract slides.pptx
# Save to file
mineru-open-api flash-extract slides.pptx -o ./out/
# Extract specific slides
mineru-open-api flash-extract slides.pptx --pages 1-5
# JSON output contains text fields per slide (requires token)
mineru-open-api extract slides.pptx -f json -o ./out/
No token needed for flash-extract. Token required for extract:
mineru-open-api auth # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable
Create token at: https://mineru.net/apiManage/token
flash-extract: no token, Markdown output to stdout (max 10 MB / 20 pages)extract -f json and read text fields from JSON output--language (default: ch, use en for English)--pages (e.g. 1-5)-f text format; Markdown output is the closest to plain text.ppt (legacy format), use ppt-extract instead-o to save to a file or directory共 1 个版本