Who is MoneyPrinterTurbo for?

Suits creators and developers who want to automate short videos; you should be comfortable with Python and getting API keys for a model provider and a stock footage service.

What can you build with MoneyPrinterTurbo?

Generate a vertical 1080x1920 explainer clip for TikTok or YouTube Shorts from a single topic. Produce a batch of short videos on related keywords for a content channel. Call the API from your own automation to create videos on a schedule. Narrate your own script over your own footage with auto-generated subtitles. Compare different language models and voice services by generating the same video with each.

harry0703 /

MoneyPrinterTurbo

Turns a topic or keyword into a finished short video with script, voice and subtitles

134.3k stars
6.3k stars since 3 Oct
Python
Updated yesterday
Some experience
Image, video & audio

Open on GitHub (opens in a new tab)

Making a short video by hand means writing a script, finding clips, recording a voiceover, timing subtitles and editing it all together. MoneyPrinterTurbo chains those steps into one automated workflow. You give it a topic or keyword, and it produces a finished video.

A language model writes or rewrites the script and picks search keywords. Footage comes from stock libraries such as Pexels, Pixabay and Coverr, from your own files, or from AI video and image services. A text-to-speech service reads the script, subtitles are generated, music is added, and the pieces are combined. Every stage can be replaced with your own content.

It works with many model providers, including OpenAI, Claude, Gemini, DeepSeek and local Ollama. You can use it through a web UI, an API, a command line or an agent. The README does not compare it with other tools by name.

What it does

Topic-to-video pipeline
Covers script, voiceover, footage, subtitles, music and editing. You can swap in your own script, voice, media or music at any step.
Many model providers
Works with OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Qwen, Azure OpenAI and more. Gateways and local runners like OpenRouter, LiteLLM and Ollama are also supported.
Flexible footage sources
Use your own images and videos, or stock clips from Pexels, Pixabay and Coverr. Several AI text-to-video services and OpenAI-compatible image generation are also supported.
Voice, subtitles and music
Voices come from Edge TTS (free, no key), Azure Speech, ElevenLabs, Kokoro and others. Subtitle font, colour, position and outline are adjustable, and music volume is set separately.
Batch output and publishing
Generates several videos at once in 9:16, 16:9 or 1:1. It can upload finished videos to TikTok, Instagram and YouTube Shorts.

What you could build

Generate a vertical 1080x1920 explainer clip for TikTok or YouTube Shorts from a single topic.
Produce a batch of short videos on related keywords for a content channel.
Call the API from your own automation to create videos on a schedule.
Narrate your own script over your own footage with auto-generated subtitles.
Compare different language models and voice services by generating the same video with each.

Get started

The README excerpt shown does not include install commands, so check the full README or the releases page on GitHub. You will need Python 3.11 or newer and an API key for at least one model provider, plus a stock footage key if you use Pexels or Pixabay.

Commands are copied from the project's README. Read it on GitHub for the full setup.

Anything better than MoneyPrinterTurbo?

MoneyPrinterTurbo is the strongest pick for automated topic-to-video: it's the most popular, actively maintained, and has a web UI, API and CLI. Look elsewhere if you want AI-generated visuals instead of stock footage, or agent-driven editing.