Skip to content
Get packs

MoneyPrinter

Python tool that generates YouTube Shorts from a topic, using local Ollama models for scripts.

GitHub Download source
Stars
14.1k
Forks
1.8k
Licence
MIT
Language
Python
Last update
7 months ago
Type
App

What it is

MoneyPrinter is a Python project that aims to automate making YouTube Shorts: you give it a video topic and it generates a script and metadata, then assembles a video. The README says script generation is powered by local Ollama models, and it uses MoviePy for video editing. It also includes a web UI and a queue-based setup with an API, worker, and Postgres in Docker.

  • Generate a short video script from a topic using a local Ollama model
  • Assemble a YouTube Shorts-style video with MoviePy from the generated content
  • Run the DB-backed generation queue in Docker for restart-safe processing
  • Review and tweak configuration via .env settings such as the ImageMagick path

Great for

  • Hobbyists who want to experiment with automated short-form video creation
  • Developers interested in combining local LLMs with video editing in Python
  • People comfortable running Ollama and configuring a local Python environment
  • Users who want to self-host rather than rely on a paid cloud video service

Not ideal for

  • People who need polished, hands-off content with no setup, since the README describes multiple setup steps and dependencies
  • Anyone who wants to contribute code, since the README says pull requests are not being accepted for the time being
  • Users who cannot run a local Ollama model, since script generation depends on it
Step-by-step guide: how to use MoneyPrinterInstall, first run, examples, tips and FAQs
MoneyPrinter vs NarratoAI

How to get it

  1. 1

    Clone and build from source

    You'll need: Ollama · ImageMagick (auto-detected from PATH, or set manually in .env) · Docker (for the containerized queue setup)

    Clone the repository

    git clone https://github.com/FujiwaraChoki/MoneyPrinter

    Start Ollama and pull a model

    ollama serve

    Pull the example model

    ollama pull llama3.1:8b
  2. 2

    Run it

    • Install Ollama and pull a model, as shown in the README FAQ
    • Install ImageMagick and confirm it is on your PATH, or set IMAGEMAGICK_BINARY in .env
    • Follow docs/quickstart.md or run the interactive setup.sh script
    • Open the web UI, select your Ollama model, and enter a video topic
  3. 3

    Get the most out of it

    • Pick an Ollama model in the UI that suits your hardware
    • Use the Docker setup from docs/docker.md for the queue-based API and worker
    • Check docs/configuration.md for settings beyond the basics
    • Consult docs/troubleshooting.md and the FAQ for common install problems

Downloads

Source code (.zip)main branch · straight from GitHub

Strengths

  • Runs script generation on local Ollama models, so no cloud LLM API is required per the README
  • Has documentation for setup, configuration, Docker, and troubleshooting
  • Released under the MIT license

Trade-offs

  • README mentions several dependencies (Ollama, ImageMagick, playsound) that can be tricky to install
  • Pull requests are not currently accepted, limiting community code contributions
  • README does not clearly describe output quality or how well it works for YouTube publishing

How it compares

ProjectStarsTypeLevelUpdatedBest for
MoneyPrinter (this)14.1kAppintermediate7 months agoHobbyists who want to experiment with automated short-form video creation
NarratoAI11.7kAppintermediate12 days agoCreators who make commentary or short-drama mashup videos
langflow156kAppintermediate4 days agoDevelopers who want a visual way to prototype LLM workflows and then move them into code
OpenHands92.5kAppintermediate4 days agoDevelopers who want coding agents running on a server while their laptop is off
huginn50.3kAppintermediate4 days agoPeople who want IFTTT-style automations without sending their data to a third-party service
LibreChat46.6kAppintermediate4 days agoTeams that want one shared chat interface across several AI providers

Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.