Skip to main content

​
Quickstart

This guide walks you through the fastest path to generating your first AI-powered video with MoneyPrinter.

​
Prerequisites

Ensure you have the following installed:
For detailed installation instructions, see the Installation Guide.

​
Setup Steps

1

Clone the repository

git clone https://github.com/FujiwaraChoki/MoneyPrinter.git
cd MoneyPrinter
2

Run the interactive setup script (recommended)

The setup script checks dependencies, creates .env, installs packages, and optionally pulls an Ollama model:
./setup.sh
Or use manual setup:
# Install dependencies
uv sync

# Create environment file
cp .env.example .env
Windows PowerShell:
Copy-Item .env.example .env
3

Configure required environment variables

Edit .env and set:
# Required
TIKTOK_SESSION_ID="your_tiktok_session_id"
PEXELS_API_KEY="your_pexels_api_key"

# Optional (defaults shown)
OLLAMA_BASE_URL="http://localhost:11434"
OLLAMA_MODEL="llama3.1:8b"
  1. Log into TikTok in your browser
  2. Open Developer Tools (F12)
  3. Go to Application → Cookies
  4. Copy the value of the sessionid cookie
  1. Create a free account at pexels.com/api
  2. Generate an API key from your dashboard
4

Start Ollama and pull a model

In a new terminal:
ollama serve
Pull a model (if not already installed):
ollama pull llama3.1:8b
Verify the model is available:
ollama list
If Ollama runs on another machine or port, set OLLAMA_BASE_URL in .env.
5

Start the backend API

uv run python Backend/main.py
The API will start on http://localhost:8080.
6

Start the worker (new terminal)

The worker claims jobs from the queue and runs the generation pipeline:
uv run python Backend/worker.py
7

Start the frontend (new terminal)

cd Frontend
python3 -m http.server 3000
Open your browser to http://localhost:3000.
8

Generate your first video

In the web interface:
  1. Enter a video subject (e.g., “Top 3 AI business ideas”)
  2. Expand Advanced Options
  3. Select an Ollama model from the dropdown
  4. Choose a voice (default: en_us_001)
  5. Click Generate
Progress events will stream in real-time. The final video will be saved as output.mp4 in the project root.

​
Verify Installation

Test the API endpoints: 
# List available Ollama models
curl http://localhost:8080/api/models

# Queue a test generation job
curl -X POST http://localhost:8080/api/generate \
  -H "Content-Type: application/json" \
  -d '{
    "videoSubject": "AI business ideas",
    "aiModel": "llama3.1:8b",
    "voice": "en_us_001",
    "paragraphNumber": 1,
    "customPrompt": ""
  }'

​
Optional: Run Tests

Install dev dependencies and run the test suite: 
uv sync --group dev
uv run pytest
See Testing for more details.

​
What’s Next?

Configuration

Learn about all environment variables and options

Docker Deployment

Run the full stack with Docker Compose

Architecture

Understand the queue-based system design

Troubleshooting

Common issues and solutions

​
Troubleshooting

  • Ensure Ollama is running: ollama serve
  • Check models are installed: ollama list
  • Verify OLLAMA_BASE_URL in .env
Set the explicit path in .env:Linux/macOS:
IMAGEMAGICK_BINARY="/usr/local/bin/magick"
Windows:
IMAGEMAGICK_BINARY="C:\\Program Files\\ImageMagick-7.1.1-Q16-HDRI\\magick.exe"
Note the double backslashes (\\) for Windows paths.
  • Ensure the backend API is running first
  • Check DATABASE_URL is correctly set (defaults to SQLite)
  • Look for errors in the worker terminal output

Build docs developers (and LLMs) love

Get started for freeTalk to us