别再用 AI 生成那些只能看不能改的 PPT 图片了！

以前试过各种 AI 做 PPT，全是图片拼接，改个字就要崩溃重做。

直到刷到这个 GitHub 的硬核神器 ppt-master（23k）

主要有以下亮点：

· 输出的是原生 .pptx，文本框、形状、图表、动画随便点随便改，再也不怕领导临时改需求 · PDF、Word、网页链接、Markdown 随便丢进去，一套流程就能生成专业幻灯片 · 自带 TTS 语音旁白 + 原生动画，生成完直接能讲 · 本地运行，套自己公司模板，数据不怕泄露

这款真是办公必备神器，感兴趣的可以看看～ 地址：https://github.com/hugohe3/ppt-master…

hugohe3/ppt-master

Source: https://github.com/hugohe3/ppt-master

PPT Master — AI generates natively editable PPTX from any document

English | 中文

_{This project is kept free and open source with the support of PackyCode, APIKEY.FUN and other sponsors.}

Thanks to PackyCode for sponsoring this project! PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. PackyCode provides special discounts for our project users: register using this link and enter the promo code ppt-master during recharge to get 10% off.

Thanks to APIKEY.FUN for sponsoring this project! APIKEY.FUN is a professional enterprise-grade AI relay service committed to stable, efficient, and low-cost AI access for businesses and developers. The platform supports mainstream models including Claude, OpenAI, and Gemini, with prices as low as 7% of official rates. Register through our dedicated link for an exclusive perk: up to 5% off on top-ups, permanently.

Live Demo · About Hugo He · Examples · FAQ · Roadmap · Contact

Download the new narrated Attention Is All You Need deck — play it in PowerPoint and every slide reads itself out loud. That's just the tip of what PPT Master can do.

Of course, you can also download any of the six example decks below — opening the raw .pptx in PowerPoint is the fastest way to see this project's real capability ceiling.

Editorial Magazine — architecture photography, calm typographic grid Flip online · Download .pptx	Data Journalism — Bloomberg-style dark dashboard, chart-driven Flip online · Download .pptx	Swiss Grid — strict modular grid, restrained type, red-accent Flip online · Download .pptx
Glassmorphism SaaS — translucent layers, gradient depth, product UI Flip online · Download .pptx	Memphis Pop — bold primaries, geometric patterns, playful energy Flip online · Download .pptx	Risograph Zine — duotone print, hand-made bookstore-culture feel Flip online · Download .pptx

_{Generated with Claude Opus 4.7 + gpt-image-2. Flip through all examples online → · examples/ directory · Why PPT Master?}

Drop in your source material and get back a real PowerPoint: directly editable, with native slide transitions and entrance animations, speaker notes you can turn into audio narration, and the option to follow your own PPT template — a complete deck you can present as-is and keep editing. How to use each capability → Getting Started.

⚠️ PPT Master is a harness, not a complete agent. harness + model = agent — the tool owns the workflow; the model sets the ceiling. To form a genuinely high-quality agent, use Claude with a large context window (~1M tokens) + AI image generation (gpt-image-2). Other models can run the pipeline but cannot reach the same quality ceiling. If results disappoint, upgrade the model — don’t blame the harness.

How it works — PPT Master is a workflow (a “skill”) that works inside AI IDEs like Claude Code, Cursor, VS Code + Copilot, or Codebuddy. You chat with the AI — “make a deck from this PDF” — and it follows the workflow to produce a real editable .pptx on your computer. No coding on your side; the IDE is just where the conversation happens.

What you’ll do: install Python, install an AI IDE, drop in your material.

Why it’s shaped this way — knowing how to use Python and AI agents will matter more and more. This project is meant to show how far you can go with just those two things. There’s a learning curve if you’re starting cold, but it’s the curve worth climbing. Making a deck is just the excuse — what I’m really pushing is Python and agents.

PPT Master is different:

• Real PowerPoint — if a file can’t be opened and edited in PowerPoint, it shouldn’t be called a PPT. Every element PPT Master outputs is directly clickable and editable
• Transparent, predictable cost — the tool is free and open source; the only cost is your AI model usage. As AI tools move to usage-based billing, you pay exactly what you consume — no separate PPT subscription added on top
• Data stays local — your files shouldn’t have to be uploaded to someone else’s server just to make a presentation. Apart from AI model communication, the entire pipeline runs on your machine
• No platform lock-in — your workflow shouldn’t be held hostage by any single company. Works with Claude Code, Cursor, VS Code Copilot, and more; supports Claude, GPT, Gemini, Kimi, and other models

AI presentation tools roughly fall into four categories. PPT Master only does the last one:

It’s a tool

PPT Master is a tool, the same way PowerPoint is a tool. With the same PowerPoint, a designer can produce something stunning while most people only ever touch a few basic features — the difference isn’t the tool, it’s the person using it.

The examples above are all ones I made with it. If you can’t get there yet, it’s most likely that you haven’t learned the workflow — start with Getting Started and the example projects. For any tool, the person who knows how to use it usually matters more than the tool itself.

The best results do need Claude. Before you call it expensive, think about what it would cost to hire someone to produce a deck at the same level. The project also supports GPT, Gemini, Kimi, and other models — the results simply differ. Expecting top-tier output while paying the lowest possible cost was never reasonable to begin with.

Built by Hugo He

I’m a finance professional (CPA · CPV · Consulting Engineer (Investment)) who regularly reviews and edits presentation decks. I wanted AI-generated slides to remain editable in PowerPoint, not flattened into images — so I built this.

🌐 Personal website · 📧 [email protected] · 🐙 @hugohe3

Quick Start

1. Prerequisites

You only need Python. Everything else is installed via pip install -r requirements.txt.

TL;DR — Install Python, run pip install -r requirements.txt, and you’re ready to generate presentations.

# macOS
brew install python
pip install -r requirements.txt

# Ubuntu / Debian
sudo apt install python3 python3-pip
pip install -r requirements.txt

# macOS
brew install pandoc

# Ubuntu / Debian
sudo apt install pandoc

2. Pick an Agent

PPT Master runs in any tool with agent capability — read/write files, execute commands, and sustain multi-turn conversation.

Model recommendation: prefer Claude Opus / Sonnet with a large context window and gpt-image-2 for images — see the note above for why.

🔑 Want to use Claude / GPT / Gemini but don’t have access yet? Project sponsors PackyCode and APIKEY.FUN can help — both offer pay-as-you-go access to Claude, GPT, Gemini and more, no subscription required. PackyCode: 10% off with promo code ppt-master at top-up. APIKEY.FUN: prices as low as 7% of official rates; register via our link for an exclusive permanent discount of up to 5% on top-ups.

3. Set Up

Option A — Download ZIP (no Git required): click Code → Download ZIP on the GitHub page, then unzip.

Option B — Git clone (requires Git installed):

git clone https://github.com/hugohe3/ppt-master.git
cd ppt-master

Then install dependencies:

pip install -r requirements.txt

To update later (Option A / B): python3 skills/ppt-master/scripts/update_repo.py

Option C — Skill marketplace: the repo ships .claude-plugin/marketplace.json, so it can be installed through the Claude Code plugin marketplace ecosystem:

# Cross-agent CLI (Claude Code, Cursor, Codex, etc.)
npx skills add hugohe3/ppt-master

# Or inside Claude Code
/plugin marketplace add hugohe3/ppt-master
/plugin install ppt-master@ppt-master

Both install paths above only fetch the skill files (not the full repo); you still need to pip install -r requirements.txt from the installed location for the post-processing scripts to run.

4. Create

Provide source materials (recommended): Place your PDF, DOCX, images, or other files in the projects/ directory, then tell the AI chat panel which files to use. The quickest way to get the path: right-click the file in your file manager or IDE sidebar → Copy Path (or Copy Relative Path) and paste it directly into the chat.

You: Please create a PPT from projects/q3-report/sources/report.pdf

Paste content directly: You can also paste text content straight into the chat window and the AI will generate a PPT from it.

You: Please turn the following into a PPT: [paste your content here...]

Either way, the AI will first confirm the design spec:

AI:  Sure. Let's confirm the design spec:
     [Template] B) Free design
     [Format]   PPT 16:9
     [Pages]    8-10 pages
     ...

The AI handles everything — content analysis, visual design, SVG generation, and PPTX export.

Output: Native-shapes .pptx (directly editable) saved to exports/<name>_<timestamp>.pptx. A copy of svg_output/ is always snapshotted to backup/<timestamp>/svg_output/ for re-export / archival. Pass --svg-snapshot to additionally emit an SVG-image preview pptx alongside the native pptx in exports/ (see FAQ). Requires Office 2016+.

AI lost context? Ask it to read skills/ppt-master/SKILL.md.

Something went wrong? Check the FAQ — it covers model selection, layout issues, export problems, and more. Continuously updated from real user reports.

5. Image Acquisition (Optional)

Two paths for non-user images, mixable per row in the same deck:

For API-backed features, put credentials in .env. Clone installs can use cp .env.example .env; skill marketplace installs should use a persistent user config:

mkdir -p ~/.ppt-master
cp /path/to/installed/ppt-master/.env.example ~/.ppt-master/.env

PPT Master reads the current process environment first, then the first .env found in this order: current working directory, skill directory (e.g. ~/.agents/skills/ppt-master/.env), clone repo root, ~/.ppt-master/.env.

A) AI generation — image_gen.py. Set IMAGE_BACKEND plus the provider’s *_API_KEY (OPENAI_API_KEY, GEMINI_API_KEY, etc.), and the pipeline calls it automatically. Run python3 skills/ppt-master/scripts/image_gen.py --list-backends for the full backend list. gpt-image-2 is currently the best default.

B) Web image search — image_search.py. Zero-config works, but configure PEXELS_API_KEY / PIXABAY_API_KEY (both free) for higher-quality results. Without keys, search uses Openverse / Wikimedia Commons only; this is useful as a fallback, but image quality can be uneven because many results are ordinary user uploads. With keys, the default provider chain also appends Pexels / Pixabay, which materially improves modern stock photography, people, workplace, lifestyle, and illustration coverage. The default is quality-first: CC0, Public Domain, Pexels / Pixabay no-attribution licenses, CC BY, and CC BY-SA are considered together, and Executor adds a small inline credit whenever the selected image requires attribution. Use --strict-no-attribution only when a slide cannot tolerate any credit line. For high-impact covers, product shots, portraits, and branded scenes, prefer this order: user-provided high-resolution assets / AI generation > web search with Pexels / Pixabay keys > zero-config web search.

Full reference: image-generator.md (AI) · image-searcher.md (web).

Documentation

Contributing

See CONTRIBUTING.md for how to get involved.

License

MIT

Acknowledgments

SVG Repo · Tabler Icons · Simple Icons · Phosphor Icons · Robin Williams (CRAP principles)

Contact & Collaboration

Looking to collaborate, integrate PPT Master into your workflow, or just have questions?

• 💬 Questions & sharing — GitHub Discussions
• 🐛 Bug reports & feature requests — GitHub Issues
• 🌐 Learn more about the author — www.hehugo.com

Star History

Sponsors & Support

PPT Master is currently built and maintained primarily by me. Every new template, bug fix, and documentation update takes ongoing resources — currently shared by the sponsors and individual supporters below.

Corporate sponsors

Individual support

If PPT Master has been helpful to you, individual support of any amount helps keep the project moving and free.

Made with ❤️ by Hugo He — if this project helps you, please give it a ⭐ and consider sponsoring.

_{Official distribution: GitHub (primary) · AtomGit (mirror). Redistributions on other platforms are unofficial. MIT licensed — attribution required.}

⬆ Back to Top