harry0703/MoneyPrinterTurbo

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 45 minutes ago
Added to GitGenius on May 31st, 2026
Created on March 11th, 2024
Open Issues & Pull Requests: 20 (+0)
Number of forks: 15,757
Total Stargazers: 103,930 (+2)
Total Subscribers: 657 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 22.9 hours
Mean response time: 64.9 days
90th percentile: 289.3 days
Tracked items: 498

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 12% of issues opened in the past year have been closed. Three people close 91% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 16
New in 7 days: 4
Closed in 7 days: 2
Avg open age: 0 days
Stale 30+ days: 3
Stale 90+ days: 0

Recent activity

Opened in 7 days: 4
Closed in 7 days: 2
Comments in 7 days: 5
Events in 7 days: 9

Top labels

  • bug (184)
  • enhancement (165)
  • suggestion (2)
  • invalid (1)

Detailed Description

MoneyPrinterTurbo is a Python-based automation tool that generates short-form videos entirely through AI, requiring only a video topic or keyword as input. The system automatically produces video scripts, sources video materials, generates subtitles, selects background music, and synthesizes everything into high-definition short videos. The project supports both a web interface and an API interface for different user preferences.

The project maintains an MVC architecture designed for clarity and maintainability, making it accessible for developers who want to extend or modify the codebase.

Core functionality includes AI-powered video script generation with customization options, support for multiple high-definition video formats including vertical 9:16 (1080x1920) and horizontal 16:9 (1920x1080) orientations, and batch video generation capabilities. Users can adjust video segment duration to control material transition frequency. The system supports both Chinese and English video scripts and offers multiple text-to-speech synthesis options with real-time preview functionality. Subtitle generation is highly customizable, allowing adjustments to font, position, color, size, and stroke effects.

Video materials come from high-quality, royalty-free sources including Pexels, Pixabay, and Coverr, with options to incorporate local materials. The project integrates TwelveLabs video AI capabilities for semantic reordering of material keywords using Marengo and content QA using Pegasus. Background music can be randomly selected or manually specified with adjustable volume levels.

The platform supports integration with numerous AI models including OpenAI, Azure, Google Gemini, Ollama, DeepSeek, MiniMax, and various others, providing flexibility in language model selection. A notable feature is one-click cross-platform publishing that automatically uploads completed videos to TikTok, Instagram, and YouTube Shorts through the Upload-Post service, with automatic AI-generated content labeling for YouTube uploads.

The repository overlaps with contributors from OpenAI Codex, LangGenius Dify, and InfiniFlow RAGFlow, suggesting cross-pollination with other AI and automation projects.

The project is sponsored by multiple organizations including Volcano Engine, which provides access to ByteDance's proprietary models, CCSub for API services, Compshare for GPU computing resources, and RecCloud which offers a free online AI video generator based on the project for users seeking deployment-free usage.