Skip to main content
All posts
Guides

MoneyPrinterTurbo: What It Is, How to Install It, and a No-Install Alternative

MoneyPrinterTurbo turns a topic into a narrated short video. Here is what it does, how to install it with pip, Docker or the Windows package, how to fix common errors, and how to make the same kind of video online with no install.

MoneyPrinterTurbo is a free, open-source short video generator on GitHub. You give it a topic or keyword; it writes the script with an AI model, finds matching footage, adds a voiceover, subtitles and background music, and exports an HD video. It is MIT licensed and has more than 140,000 GitHub stars as of November 2026.

This guide covers what it does, how to install it, the errors people hit most often, and how to make the same kind of video online, with no install.

ViralEffects is not affiliated with MoneyPrinterTurbo. Everything below about MoneyPrinterTurbo comes from its official README (version 1.3.10, November 2026).

What MoneyPrinterTurbo does

The project's own one-line description: provide a video topic or keyword, and it generates the script, matches footage, creates subtitles and background music, and produces an HD short video.

The pipeline, step by step:

  1. Script. An AI model writes a script from your topic, in several languages, or you paste your own. Supported providers include OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Qwen, Kimi, xAI Grok and local models through Ollama.
  2. Footage. Clips come from free stock libraries (Pexels, Pixabay) or Coverr, from your own images and videos, or from paid AI video APIs.
  3. Voiceover. Edge TTS is free and needs no API key. Azure, ElevenLabs, Gemini, MiniMax, Fish Audio and others are supported too.
  4. Subtitles. Timed from the TTS output by default, or transcribed locally with faster-whisper for a more accurate timeline.
  5. Music and export. Background music with its own volume, then export in 9:16 (1080×1920), 16:9 (1920×1080) or 1:1 (1080×1080).

You can drive it from a web UI, a REST API, a command-line tool or an AI agent, and generate batches of videos.

System requirements

From the README:

MinimumRecommended
CPU4 cores6 to 8 cores
RAM4 GB8 GB
GPUNot required4+ GB VRAM
  • Windows 10+, macOS 11+ or a mainstream Linux distribution.
  • Python 3.11 or later for local installs.
  • A GPU only speeds up local Whisper subtitles and batch jobs. If you use cloud models and online footage, CPU and RAM matter more.

How to install MoneyPrinterTurbo

Option 1: pip (easiest if you have Python)

The official PyPI package is called mpt. The package named MoneyPrinterTurbo on PyPI is maintained by a third party, not by the project's author.

python3 -m venv .venv
source .venv/bin/activate      # Windows: .venv\Scripts\Activate.ps1
python -m pip install mpt
mpt webui

The web UI opens in your browser. Add your API keys (AI model, footage source, voice) in its basic settings. Generated videos are saved under storage/tasks in the app's data folder:

  • macOS: ~/Library/Application Support/MoneyPrinterTurbo
  • Windows: %LOCALAPPDATA%\MoneyPrinterTurbo
  • Linux: ~/.local/share/MoneyPrinterTurbo

To upgrade: python -m pip install --upgrade mpt.

Option 2: Windows one-click package

Download the .7z file from the Assets section of the latest release. The "Source code" zip files only contain source code and do not include start.bat. Extract the archive, run update.bat, then run start.bat.

Option 3: Docker

git clone https://github.com/harry0703/MoneyPrinterTurbo.git
cd MoneyPrinterTurbo
cp config.example.toml config.toml
docker compose -f docker-compose.release.yml up

The web UI runs at http://127.0.0.1:8501 and the API docs at http://127.0.0.1:8080/docs.

Option 4: Google Colab

The README links a Colab notebook if you would rather not install anything locally.

Option 5: From source with uv

git clone https://github.com/harry0703/MoneyPrinterTurbo.git
cd MoneyPrinterTurbo
uv python install 3.11
uv sync --frozen
sh webui.sh            # Windows: .\webui.bat

On Windows, keep the project in a folder whose path has no spaces, special characters or non-ASCII characters.

Common MoneyPrinterTurbo errors and fixes

These come from the README's troubleshooting section.

RuntimeError: No ffmpeg exe could be found FFmpeg usually downloads automatically. If it can't, download FFmpeg yourself and set its path in config.toml:

[app]
ffmpeg_path = "C:\\path\\to\\ffmpeg.exe"

OSError: [Errno 24] Too many open files Your system's open-file limit is too low. Check it with ulimit -n and raise it, for example ulimit -n 10240.

Whisper model download failed (LocalEntryNotFoundError) The Whisper subtitle model (about 3 GB for large-v3) downloads from Hugging Face on first use. If that fails, download faster-whisper-large-v3 manually and put the folder at MoneyPrinterTurbo/models/whisper-large-v3. You can also skip Whisper and keep the default edge subtitle mode, which needs no model.

Installed the wrong package If pip install MoneyPrinterTurbo behaves differently from the docs, that's the third-party package. Uninstall it and install mpt.

What MoneyPrinterTurbo is best at

MoneyPrinterTurbo is built for narrated, topic-driven videos: explainers, facts, tips and listicles, where a voice reads a script over stock or AI footage. Its own gallery shows topics like the science of coffee and the history of flight.

What you take on in exchange for a free tool:

  • Setup. A Python, Docker or Colab environment, plus API keys for an AI model and footage source.
  • Running costs. The software is free, but paid AI models, voices and AI video APIs bill you separately. Edge TTS and the Pexels and Pixabay APIs are free.
  • The look. With the default stock libraries, footage is generic stock that matches your script's keywords, not footage of you.

Run it online: MoneyPrinterTurbo-style videos with no install

If you want the same kind of video without setting anything up, use our MoneyPrinterTurbo Online page. It's an independent tool inspired by MoneyPrinterTurbo. It doesn't run the project's code, and it isn't affiliated with its author.

You type a topic, pick a voice, and press Generate. The topic sets the length, up to 60 seconds. Then:

  1. An AI model writes the script and picks footage search terms.
  2. Matching stock clips come from Pixabay.
  3. An AI voice reads the script, and captions highlight each word as it's spoken.
  4. You get a 720×1280 vertical MP4, saved in My videos. Most videos are ready in 2 to 5 minutes.
MoneyPrinterTurboMoneyPrinterTurbo Online
You start withA topic, keyword or your own scriptA topic
SetupPython, Docker or Colab, plus API keysNone, runs in the browser
Formats9:16, 16:9, 1:19:16 (720×1280)
LengthYou chooseSet by the topic, up to 60 seconds
FootagePexels, Pixabay, Coverr, your own files or AI videoPixabay stock
Background musicYesNo
CostFree software; you pay your own API providers40 credits a video
Source codeOpen source (MIT)Hosted service

The short version: run MoneyPrinterTurbo yourself if you want full control, other formats, background music or batches, and don't mind the setup. Use MoneyPrinterTurbo Online if you just want a narrated vertical video from a topic in a few minutes.

Effects starring your own photos

Not every short video is a narrated explainer. Many are effects starring real people: two friends hugging, someone doing a trending dance, an old family photo coming to life. For these you start from a photo, not a topic:

  • AI Hug: two photos become a 5-second hug video.
  • Old Photo to Life: people in an old photo blink, smile and move. Black-and-white photos work.
  • AI Dance: one full-body photo, five dance styles, 10 seconds.
  • Earth Zoom Out: the camera pulls back from you out to space.
  • 360° Orbit: the camera circles your subject.

Every tool on ViralEffects uses the same credits. Credit packs start at $4.99 for 100 credits, credits never expire, videos have no watermark, and failed videos are refunded automatically. There are no free credits. See pricing.

FAQ

Is MoneyPrinterTurbo free?

Yes. The software is open source under the MIT license. You may still pay for the AI model, voice or AI video APIs you connect to it. Edge TTS voices and the Pexels and Pixabay footage APIs are free.

Is there a MoneyPrinterTurbo online version?

The project itself runs on your own computer, in Docker or in Google Colab. To make the same kind of video in your browser, use MoneyPrinterTurbo Online, an independent tool that turns a topic into a narrated, captioned vertical video. MoneyPrinterTurbo's README also thanks RecCloud, which offers a free online AI video generator based on the project.

What is the official MoneyPrinterTurbo pip package?

mpt, maintained by the project's author, harry0703. Install it with pip install mpt and start it with mpt webui.

Does MoneyPrinterTurbo need a GPU?

No. A GPU with 4 GB or more of VRAM speeds up local Whisper subtitles and batch generation, but cloud models and online footage run fine on CPU.

Can MoneyPrinterTurbo make a video from my own photos?

It can use your own images and videos as footage in a narrated video. To turn a photo into an effect such as a hug, a dance or an old photo coming to life, use a photo-to-video effect tool like ViralEffects.