harry0703/MoneyPrinterTurbo
An open-source tool that turns a single topic or keyword into a finished short video, complete with script, footage, subtitles, and music
MoneyPrinterTurbo is a Python project that takes a topic or keyword, writes a video script with an AI large language model, finds matching footage, and adds subtitles and background music to produce a finished HD short video. It lets users choose among several script-writing AI providers, text-to-speech voices, free stock footage sources, and subtitle generation methods depending on their needs. It offers four ways to use it, WebUI, API, command line, and an AI agent, and can automatically publish finished videos to TikTok, Instagram, and YouTube Shorts.
What it does
- Given just a topic or keyword, an AI model can auto-write the video script, or a user-supplied custom script can be used instead
- Supports high-definition vertical video (1080x1920) and horizontal video (1920x1080), and can batch-generate multiple videos at once to pick the best one
- Voice narration can be generated with free Edge TTS or paid options like Azure, Google Gemini, and ElevenLabs, while subtitles can use fast TTS timestamps or a local speech-to-text model called whisper for more accurate timing
- Connects to many large language model providers including Kimi, OpenAI, Gemini, DeepSeek, and Alibaba's Qwen, and pulls footage from free stock sites like Pexels, Pixabay, and Coverr or from local files
- Finished videos can be auto-uploaded to TikTok, Instagram, and YouTube Shorts with one configuration, and the project supports several install paths including a Windows one-click package, Docker, and uv-based setup
Why it matters
It lowers the barrier to making short-form video content, letting anyone turn a written idea into a finished video without editing skills. It's also a concrete example of chaining multiple AI services, script generation, voice, subtitles, and footage matching, into one working pipeline.
Terms in this repo
- Large Language Model (LLM) · An AI model trained on large amounts of text that can generate human-like writing
- TTS (text-to-speech) · Technology that converts written text into spoken audio
- whisper · An open-source speech-to-text AI model, used here to align subtitle timing with the audio
- WebUI · A browser-based interface for controlling the tool with clicks instead of code
- API · An interface that lets other programs call the tool's features directly from code
Repository description (English)
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.
Open on GitHubTrending repos
- vorssaint/vorssaint-utilsOne free menu bar app replaces a dozen paid Mac utilities
- Alishahryar1/free-claude-codeA local proxy that lets coding AI agents run on 49 free or cheap model providers instead of one paid service
- freestylefly/awesome-gpt-image-2A library of 532 reverse-engineered prompts that turn GPT-Image2 into a predictable image-making tool
- block/buzzAn open-source workspace where humans and AI agents chat, code, and review in the same rooms
- NousResearch/hermes-agentNous Research's Hermes is an AI agent that gets smarter the more you use it
- virgiliojr94/book-to-skillA tool that turns technical book PDFs into on-demand reference skills for AI coding agents
- VoltAgent/awesome-agent-skillsA single hub collecting over 1000 'how-to' manuals that make AI coding assistants act like experts
- anthropics/claude-plugins-communityA shared shelf where anyone's Claude add-ons get listed for install