Content · Video, clips, voice and images, from one idea. · a tool
The open-source project MoneyPrinterTurbo, by harry0703
“Generate HD short videos from a topic or keyword with an automated AI workflow.” — the project's own words, on GitHub
Paste this into the AI that runs on your computer. It does the install, checks it works, and tells you what to type first. If anything fails, paste the error back to it.
Install MoneyPrinterTurbo (https://github.com/harry0703/MoneyPrinterTurbo) on this computer and get it working for me. I am not a developer; explain each step in one line as you go and never skip one. You are Claude Code, running on my machine. 1. Check what this machine already has (git, Python or Node as the project needs, Docker if the README says so). Tell me anything missing and install it, asking me before anything that needs my password. 2. Clone https://github.com/harry0703/MoneyPrinterTurbo into ~/tools/moneyprinterturbo and follow the README's install exactly. 3. Configure it. If it needs an API key or a login, stop and ask me for it; never guess one and never store it anywhere except where the README says. Tool-specific notes: On first launch it copies config.example.toml to config.toml itself — add your AI script-writing key (or point it at a local Ollama setup) inside the WebUI's basic settings before generating anything. Launch the WebUI with sh webui.sh (webui.bat on Windows); it opens automatically at a local port. For the API instead, run uv run python main.py. Smoke-test from the command line with: uv run python cli.py --video-subject "How AI is changing everyday life" — if subtitle_provider is set to whisper, the first run downloads a 1.6-3GB transcription model, so expect a pause there. If it reports it cannot find ffmpeg, download it manually and set ffmpeg_path in config.toml — the automatic download does not always succeed. 4. Run the smallest test the README gives, and show me the output. 5. When it works, tell me what to type first, in one line, for this job: Generate one test video. If anything fails, show me the exact error and fix it before going on.
Install MoneyPrinterTurbo (https://github.com/harry0703/MoneyPrinterTurbo) on this computer and get it working for me. I am not a developer; explain each step in one line as you go and never skip one. You are Kimi, running on my machine. 1. Check what this machine already has (git, Python or Node as the project needs, Docker if the README says so). Tell me anything missing and install it, asking me before anything that needs my password. 2. Clone https://github.com/harry0703/MoneyPrinterTurbo into ~/tools/moneyprinterturbo and follow the README's install exactly. 3. Configure it. If it needs an API key or a login, stop and ask me for it; never guess one and never store it anywhere except where the README says. Tool-specific notes: On first launch it copies config.example.toml to config.toml itself — add your AI script-writing key (or point it at a local Ollama setup) inside the WebUI's basic settings before generating anything. Launch the WebUI with sh webui.sh (webui.bat on Windows); it opens automatically at a local port. For the API instead, run uv run python main.py. Smoke-test from the command line with: uv run python cli.py --video-subject "How AI is changing everyday life" — if subtitle_provider is set to whisper, the first run downloads a 1.6-3GB transcription model, so expect a pause there. If it reports it cannot find ffmpeg, download it manually and set ffmpeg_path in config.toml — the automatic download does not always succeed. 4. Run the smallest test the README gives, and show me the output. 5. When it works, tell me what to type first, in one line, for this job: Generate one test video. If anything fails, show me the exact error and fix it before going on.
Install MoneyPrinterTurbo (https://github.com/harry0703/MoneyPrinterTurbo) on this computer and get it working for me. I am not a developer; explain each step in one line as you go and never skip one. You are Gemini CLI, running on my machine. 1. Check what this machine already has (git, Python or Node as the project needs, Docker if the README says so). Tell me anything missing and install it, asking me before anything that needs my password. 2. Clone https://github.com/harry0703/MoneyPrinterTurbo into ~/tools/moneyprinterturbo and follow the README's install exactly. 3. Configure it. If it needs an API key or a login, stop and ask me for it; never guess one and never store it anywhere except where the README says. Tool-specific notes: On first launch it copies config.example.toml to config.toml itself — add your AI script-writing key (or point it at a local Ollama setup) inside the WebUI's basic settings before generating anything. Launch the WebUI with sh webui.sh (webui.bat on Windows); it opens automatically at a local port. For the API instead, run uv run python main.py. Smoke-test from the command line with: uv run python cli.py --video-subject "How AI is changing everyday life" — if subtitle_provider is set to whisper, the first run downloads a 1.6-3GB transcription model, so expect a pause there. If it reports it cannot find ffmpeg, download it manually and set ffmpeg_path in config.toml — the automatic download does not always succeed. 4. Run the smallest test the README gives, and show me the output. 5. When it works, tell me what to type first, in one line, for this job: Generate one test video. If anything fails, show me the exact error and fix it before going on.
Install MoneyPrinterTurbo (https://github.com/harry0703/MoneyPrinterTurbo) on this computer and get it working for me. I am not a developer; explain each step in one line as you go and never skip one. You are Codex, running on my machine. 1. Check what this machine already has (git, Python or Node as the project needs, Docker if the README says so). Tell me anything missing and install it, asking me before anything that needs my password. 2. Clone https://github.com/harry0703/MoneyPrinterTurbo into ~/tools/moneyprinterturbo and follow the README's install exactly. 3. Configure it. If it needs an API key or a login, stop and ask me for it; never guess one and never store it anywhere except where the README says. Tool-specific notes: On first launch it copies config.example.toml to config.toml itself — add your AI script-writing key (or point it at a local Ollama setup) inside the WebUI's basic settings before generating anything. Launch the WebUI with sh webui.sh (webui.bat on Windows); it opens automatically at a local port. For the API instead, run uv run python main.py. Smoke-test from the command line with: uv run python cli.py --video-subject "How AI is changing everyday life" — if subtitle_provider is set to whisper, the first run downloads a 1.6-3GB transcription model, so expect a pause there. If it reports it cannot find ffmpeg, download it manually and set ffmpeg_path in config.toml — the automatic download does not always succeed. 4. Run the smallest test the README gives, and show me the output. 5. When it works, tell me what to type first, in one line, for this job: Generate one test video. If anything fails, show me the exact error and fix it before going on.
Give it a simple topic like "how coffee is grown" and generate a single portrait video end to end — this confirms the script, voice, footage, and render steps all work together.
Watch it back and confirm the narration actually matches what is on screen — footage is matched by keyword, so a vague topic tends to produce vaguer, more generic matches.
Once a single video works, queue a small JSON batch of two or three topics and confirm each finishes independently — this is how you would scale past one-off runs.
harry0703/MoneyPrinterTurbo on GitHub, under the MIT licence. 121,646 stars, checked 9 September 2026. Last change 9 September 2026. We did not write it; we checked it, and wrote this page so you can use it.
AutoClip watches a long video for you and pulls out the interesting parts.
ComfyUI is a node-based studio for building AI image, video, and audio generation into a repeatable process, rather than typing one prompt at a time into a chat box.
Pixelle-Video turns a single topic into a finished short video, end to end, through a web page rather than a code editor.
If you're launching or growing a brand across Asia and the West, a call is where we work out whether it's a fit.