Ppt Ocr

核心功能：基于MinerU实现新旧格式PPT的OCR识别，支持本地文件与URL输入，提取图片/扫描版幻灯片文字，VLM模式适配复杂布局，输出可编辑搜索的Markdown。典型场景：处理扫描生成的PPT、图片型幻灯片、老旧PPT，需转不可编辑内容为文本时使用。输入为.ppt/.pptx文件或链接，需配置MinerU Token，可指定语言、页码范围。

mzlzyca

热度 46.40

最近更新 2026-05-11 17:39:00

分类：效率依赖：第三方 API / 读写文件应用场景：文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add ppt-ocr

Metadata

name: ppt-ocr
description: OCR for PowerPoint (.ppt, .pptx) presentations with scanned or image-embedded slides. Uses MinerU to extract text from image-based presentation content. Features: OCR for image-based slides. VLM mode for complex visual layouts. Handles old .ppt and modern .pptx formats. Converts image content to readable Markdown. Use when you need to: OCR a PowerPoint file, extract text from image slides, read scanned content in presentations. Use when asked: 'how do I OCR PowerPoint slides', 'extract text from image-based ppt', 'my slides are images not text', 'can my agent OCR ppt files', 'is there a skill for PPT OCR'. Built on MinerU by OpenDataLab (Shanghai AI Lab) with advanced OCR capabilities. Ideal for converting legacy or image-heavy presentations into editable, searchable text.
homepage: https://mineru.net
metadata: {"openclaw":{"emoji":"📄","requires":{"bins":["mineru-open-api"],"env":["MINERU_TOKEN"]},"primaryEnv":"MINERU_TOKEN","install":[{"id":"npm","kind":"node","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via npm"},{"id":"go","kind":"go","package":"github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api","bins":["mineru-open-api"],"label":"Install via go install","os":["darwin","linux"]}]}}

Ppt Ocr

Convert and extract content from .ppt using MinerU (mineru-open-api).

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# OCR extraction (requires token)
mineru-open-api extract slides.ppt --ocr -o ./out/

# From URL
mineru-open-api extract https://example.com/slides.ppt --ocr -o ./out/

Authentication

Token required for extract and crawl:

mineru-open-api auth            # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

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

Capabilities

Supports local files and URLs
Requires token (mineru-open-api auth or MINERU_TOKEN env)
Supported input: .ppt
Language hint with --language (default: ch, use en for English)
Page range with --pages (where applicable)

Notes

.ppt requires extract with token. Add --ocr for image-heavy slides.
Output goes to stdout by default; use -o <dir> to save to file
Binary formats (docx) require -o flag (cannot stream to stdout)
All progress/status messages go to stderr
MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU