---

✨ What's New in 2.0

🆕 📄 Reference Document Upload - Upload project reports, data analysis, meeting notes, etc. AI automatically extracts key points

🆕 📊 Chart/Material Embedding - Upload Excel tables or screenshots, AI directly embeds them into corresponding pages

🆕 💬 Material Description - Add descriptions to each material for more precise AI understanding

---

🔄 January 30, 2025 Update

🗜️ Image Compression Optimization - Generated PPT images automatically compressed to JPEG format (85% quality), reducing file size by over 60% for faster frontend loading

---

🔄 January 29, 2025 Update

🎉 Completion Notification - Pop-up dialog after PPT generation completes, quick access to ZIP/PDF download or fine-tuning mode

⏳ Upload Loading Optimization - Loading animation during material upload, dialog cannot be closed until upload completes to prevent accidental operations

🔄 Regeneration Animation - Overlay animation when regenerating single page, clearly showing current status

📁 File Format Validation - Template and Logo uploads now validate file formats, only PNG/JPG/WebP/GIF supported, EMF/SVG vector formats not supported

💡 Format Hints Optimization - Upload areas display clear format instructions to prevent users from uploading unsupported file types

---

🔄 January 28, 2025 Update

📝 Per-Page Theme Setting - After selecting page count, set individual themes for each page for more precise AI outline generation

✏️ Outline Preview Editing - After outline generation, edit titles and content directly in the right preview panel, click "Apply Edits" to sync

🎯 Image Fine-tuning Mode - Click on generated pages to enter fine-tuning mode, only modify specified parts while keeping other elements unchanged

🔢 Page Number Control - Option to hide page numbers in Advanced Settings → Layout Settings

---

✨ Highlights

🚀 One-Click Generation - Input your topic or ideas, AI automatically generates complete PPT from outline to design

🎙️ Voice Transcription - Upload meeting recordings, AI transcribes and organizes into structured presentations

📄 Document Understanding - Upload PDF/Word/PPT/Excel documents, AI automatically extracts key information

📊 Material Embedding - Upload charts, screenshots, data tables for specific pages, AI directly embeds them into PPT

🎨 Multiple Styles - Built-in presets like Business Minimal and Tech Cool, with full customization support

🖼️ AI Image Generation - Powered by Google Gemini model, generating professional visuals for each slide

📝 Real-time Collaboration - Interactive editing of outlines and designs, AI understands your feedback instantly

🎯 Precise Control - Custom colors, fonts, page count, and logos to meet enterprise VI requirements

---

📸 Screenshots

Overview Introduction

Login Page

Workbench

Generation Process

Design Results

📊 Table Data Embedding

---

🎬 Complete Workflow

┌─────────────────────────────────────────────────────────────────┐
│  Step 1: 📝 Enter Your Idea                                     │
│  ─────────────────────────────────────────────────────────────  │
│  "Create a PPT about 2026 AI trends for investors,              │
│   data-driven, around 10 pages"                                 │
│                                                                  │
│  💡 Upload meeting recordings for AI transcription               │
│  📄 Upload reference docs (PDF/Word/PPT/Excel), AI extracts key points │
└─────────────────────────────────────────────────────────────────┘
                                 ↓
┌─────────────────────────────────────────────────────────────────┐
│  Step 2: 🎨 Choose Style & Configure Parameters                 │
│  ─────────────────────────────────────────────────────────────  │
│  • Style Presets: Business Minimal / Tech Cool / Custom         │
│  • Content Density: Rich Content / Minimalist / Follow Style    │
│  • Page Control: Auto or specify 1-20 pages                     │
│  • Advanced: Color Scheme / Fonts / Logo / Template             │
└─────────────────────────────────────────────────────────────────┘
                                 ↓
┌─────────────────────────────────────────────────────────────────┐
│  Step 3: 📋 AI Generates Outline (Editable)                     │
│  ─────────────────────────────────────────────────────────────  │
│  Page 1: Cover - 2026 AI Trends Outlook                         │
│  Page 2: Market Size - Trillion-Dollar Opportunity              │
│  Page 3: Tech Breakthroughs - Multimodal & Agents               │
│  ...                                                             │
│                                                                  │
│  ✏️ Not satisfied? Tell AI your feedback for instant adjustment │
│  📊 Upload chart materials (images/Excel/pasted tables) for specific pages, auto-embedded during generation │
└─────────────────────────────────────────────────────────────────┘
                                 ↓
┌─────────────────────────────────────────────────────────────────┐
│  Step 4: 🎯 AI Generates Design Plan (Editable)                 │
│  ─────────────────────────────────────────────────────────────  │
│  Detailed design concepts and visual plans for each page:       │
│  • Page layout structure                                        │
│  • Color application guidelines                                 │
│  • Chart/graphic recommendations                                │
│                                                                  │
│  ✏️ Not satisfied? Keep chatting to refine until perfect        │
└─────────────────────────────────────────────────────────────────┘
                                 ↓
┌─────────────────────────────────────────────────────────────────┐
│  Step 5: 🖼️ AI Generates PPT Images Page by Page               │
│  ─────────────────────────────────────────────────────────────  │
│  🎨 Generating page 3/10...                                     │
│  ████████████████░░░░░░░░░░░░ 50%                               │
│                                                                  │
│  📊 Uploaded materials are auto-embedded into corresponding pages │
│  ✏️ Single page not right? Click thumbnail and provide feedback │
└─────────────────────────────────────────────────────────────────┘
                                 ↓
┌─────────────────────────────────────────────────────────────────┐
│  Step 6: 📥 Download Your Creation                              │
│  ─────────────────────────────────────────────────────────────  │
│  • ZIP download (all images)                                    │
│  • One-click PDF export                                         │
│  • Use WPS [PDF to PPT] tool for further editing                │
└─────────────────────────────────────────────────────────────────┘

---

🛠️ Architecture

┌─────────────────────────────────────────────────────────────────┐
│                        Frontend                              │
│  React 18 + Responsive Design + Dark/Light Theme             │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                        Backend                               │
│  FastAPI + Python 3.10+ + Async Architecture                 │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                      AI Services                             │
│  Google Gemini (Text Generation + Image Generation)          │
│  iFlytek (Speech-to-Text)                                    │
└─────────────────────────────────────────────────────────────────┘

---

🚀 Quick Start

Requirements

• Python 3.10+
• Node.js 18+
• Google Gemini API Key

Installation

# 1. Clone the repository
git clone https://github.com/tonyqinatcmu/SlideBot.AI.git
cd SlideBot.AI

# 2. Install backend dependencies
pip install -r requirements.txt

# 3. Configure environment variables
cp .env.example .env
# Edit .env file and add your API keys

# 4. Install frontend dependencies and build
cd frontend
npm install
npm run build
cd ..

# 5. Start the server
python server.py

Visit http://localhost:8001 to get started!
The default invite code is "VISITOR". You can modify it in the invite_codes.json file.

⚙️ Configuration

Configure the following parameters in .env:

# Google Gemini API (Required)
GEMINI_API_KEY=your_gemini_api_key

# iFlytek Speech-to-Text (Optional, for voice transcription)
IFLYTEK_APP_ID=your_iflytek_app_id
IFLYTEK_API_SECRET=your_iflytek_api_secret

# Server Configuration
PORT=8001
HOST=0.0.0.0

Getting API Keys

Service	Purpose	Get Key
Google Gemini	Text/Image Generation	Google AI Studio
iFlytek	Voice Transcription (Optional)	iFlytek Platform

---

📁 Project Structure

slidebot/
├── server.py              # Backend main program (FastAPI routes)
├── requirements.txt       # Python dependencies
├── .env.example           # Environment variables example
├── .gitignore             # Git ignore configuration
├── LICENSE                # MIT License
├── invite_codes.json      # Invite code configuration
│
├── modules/               # Backend modules (modular architecture)
│   ├── __init__.py       # Module exports
│   ├── config.py         # Configuration constants (API keys, paths, etc.)
│   ├── prompts.py        # AI prompt templates
│   ├── models.py         # Pydantic data models
│   ├── asr.py            # iFlytek speech-to-text
│   ├── invite_codes.py   # Invite code management
│   ├── session.py        # Session state management
│   ├── gemini_api.py     # Gemini API wrapper
│   └── visit_counter.py  # Visit counter
│
├── frontend/              # React frontend
│   ├── src/
│   │   ├── App.js        # Main component (all UI logic)
│   │   └── index.js      # Entry point
│   ├── public/
│   │   ├── index.html
│   │   └── wps-tip.png   # WPS tip image
│   └── package.json
│
├── docs/                  # Documentation resources
│   └── images/           # README screenshots
│
├── outputs/               # Generated image outputs (auto-created)
├── references/            # Uploaded reference files (auto-created)
├── audio/                 # Audio files (auto-created)
└── records/               # Usage records (auto-created)

---

🎨 Features

Core Features

Feature	Description
🤖 Smart Outline	Auto-generate structured PPT outline with real-time editing
🎨 Style Design	AI generates detailed design for each page
🖼️ Image Generation	Professional visuals using Gemini, 2K/4K resolution
📝 Real-time Iteration	Conversational interaction, adjust anytime
📥 Multi-format Export	ZIP package and one-click PDF export

Advanced Features

Feature	Description
🎙️ Voice Transcription	Upload recordings, AI organizes into PPT
🏢 Template Support	Upload corporate templates for VI consistency
🎯 Custom Colors	Flexible primary, secondary, accent color settings
📝 Custom Fonts	Separate Chinese and English font settings
📊 Content Density	Switch between data-rich and minimalist styles
🌙 Dark Mode	Support dark/light theme switching

🚧 Roadmap (TODO)

• Smart outline generation with iterative editing
• AI design style generation
• Gemini image generation page by page
• Voice transcription to PPT
• Custom colors, fonts, and logo
• ZIP / PDF multi-format export
• Material Upload - Support uploading PDF, Word, PPT, Excel, images, etc. AI auto-extracts and organizes
• Speech Script Generation - Generate accompanying speech scripts alongside PPT
• Style Persistence - Save user's personalized style preferences for future sessions

---

🔧 Development Guide

Local Development

# Backend development (hot reload)
uvicorn server:app --reload --port 8001

# Frontend development
cd frontend
npm start

Production Deployment

Recommended deployment methods:

# Production deployment
uvicorn server:app --host 0.0.0.0 --port 8001

# Or use Docker (write your own Dockerfile)

Combine with Nginx reverse proxy and Systemd service management for a more stable production environment.

---

🤝 Contributing

We welcome all forms of contributions!

1. Fork the project
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

📄 License

This project is licensed under the MIT License.

---

Open Source Projects

• Google Gemini - Multimodal AI model
• iFlytek - Speech-to-text service
• FastAPI - Modern high-performance Python web framework
• React - User interface library

---

⭐ Star History

If this project helps you, please give us a Star ⭐

---

👨‍💻 Contact the Authors

---