MoneyPrinterTurbo - AI-Powered Short Video Generation Tool

Project Overview

MoneyPrinterTurbo is an open-source AI-powered short video automatic generation tool based on large AI models. It can automatically generate high-quality short video content through simple keyword or topic input. This project utilizes artificial intelligence technology to automate the entire process, including video script creation, material matching, voiceover generation, and subtitle addition.

Core Features

🎯 Intelligent Content Generation

• AI Copywriting Generation: Supports automatic generation of video scripts based on keywords, and also supports custom copywriting content.
• Multi-Language Support: Supports Chinese and English video copywriting generation.
• Batch Generation: Can generate multiple video versions at once, making it easy to choose the best effect.

🎬 Diverse Video Formats

• Vertical Screen Mode: 9:16 aspect ratio, 1080x1920 resolution, suitable for short video platforms such as TikTok and Kuaishou.
• Horizontal Screen Mode: 16:9 aspect ratio, 1920x1080 resolution, suitable for platforms such as YouTube and Bilibili.
• Segment Duration Control: Customizable video segment duration to adjust material switching frequency.

🎙️ Professional Voiceover System

• Multiple Speech Synthesis: Supports multiple AI voices, with real-time listening effects.
• GPT-SoVITS Voiceover: Provides more natural and emotionally rich speech synthesis.
• Azure Speech Services: Adds 9 new Azure high-quality speech synthesis options.

📝 Intelligent Subtitle Function

• Automatic Subtitle Generation: Supports Edge and Whisper subtitle generation methods.
• Subtitle Style Customization: Adjustable font, position, color, size, and stroke effects.
• High-Precision Recognition: Whisper mode provides more reliable subtitle quality.

🎵 Background Music Integration

• Music Library Support: Built-in background music resources.
• Volume Control: Adjustable background music volume.
• Custom Music: Supports uploading local music files.

🖼️ High-Quality Material Sources

• Copyright-Free Materials: Provides high-definition copyright-free video materials.
• Local Material Support: Can use your own local video materials.
• Intelligent Matching: Optimizes the matching degree of video materials and copywriting.

Technical Architecture

🏗️ System Architecture

• MVC Architecture: Complete Model-View-Controller architecture design.
• Clear Code Structure: Easy to maintain and extend.
• Dual Interface Support: Provides both API interface and Web user interface.

🤖 AI Model Support

The project supports access to various mainstream AI models:

• OpenAI GPT series
• Moonshot
• Azure OpenAI
• Tongyi Qianwen (Alibaba Cloud)
• Google Gemini
• DeepSeek
• ERNIE Bot (Baidu)
• Ollama Local Deployment
• gpt4free Free Solution
• one-api Unified Interface

💻 System Requirements

• Minimum Configuration: CPU 4 cores, Memory 4GB
• Operating System: Windows 10+ or MacOS 11.0+
• Graphics Card: Not required, but GPU can accelerate processing
• Network: Requires a stable network connection to access AI services

Deployment Methods

🚀 One-Click Startup Package

• Provides a Windows one-click startup package, which can be used after downloading and decompressing.
• Baidu Netdisk and Google Drive download links.
• Supports automatic update function.

🐳 Docker Deployment

git clone https://github.com/harry0703/MoneyPrinterTurbo.git
cd MoneyPrinterTurbo
docker-compose up

🛠️ Source Code Deployment

git clone https://github.com/harry0703/MoneyPrinterTurbo.git
cd MoneyPrinterTurbo
conda create -n MoneyPrinterTurbo python=3.11
conda activate MoneyPrinterTurbo
pip install -r requirements.txt

Configuration Instructions

🔧 Basic Configuration

1. Copy config.example.toml to config.toml
2. Configure Pexels API key (video material source)
3. Select and configure AI model provider API key
4. Set ImageMagick path (image processing)
5. Configure FFmpeg path (video processing)

🎛️ Function Configuration

• Subtitle Generation Method: Edge (fast) or Whisper (high quality)
• Speech Synthesis Service: Choose a suitable TTS service provider
• Video Output Settings: Resolution, duration, transition effects, etc.

Usage Process

1. Enter Theme: Provide video theme or keywords
2. AI Generates Script: The system automatically creates video copywriting
3. Material Matching: Intelligently select relevant high-definition video materials
4. Voiceover Generation: Convert copywriting into natural speech
5. Subtitle Addition: Automatically generate and add subtitles
6. Background Music: Add appropriate background music
7. Video Synthesis: Generate the final high-definition short video

Project Advantages

✨ Technical Advantages

• Fully Open Source: Code is open, freely customizable
• Multi-Model Support: Does not rely on a single AI service provider
• High-Quality Output: Supports 1080p high-definition video generation
• Full Process Automation: One-click completion from copywriting to finished product

🎯 User Friendly

• Web Interface: Intuitive graphical operation interface
• API Interface: Supports programmatic calls and integration
• Detailed Documentation: Complete deployment and usage instructions
• Video Tutorials: Provides complete usage demonstrations

Application Scenarios

• Content Creation: Individual creators quickly produce short video content
• Marketing Promotion: Companies quickly generate product promotional videos
• Education and Training: Produce teaching short videos and knowledge sharing content
• Social Media: Batch generation of social platform content
• E-commerce Live Streaming: Quickly create product introduction videos