AiBOX.im

MoneyPrinterTurbo

AI short-video generator from a topic (trending Chinese tool)

— views · — installs
Windows Difficulty ●●●○○ stable v1.3.10
MoneyPrinterTurbo icon

MoneyPrinterTurbo · icon from the registry

System requirements

No extra runtime needed

This app ships with everything it needs — no Node.js, Python or other runtimes to install.

Platforms

Windows

AI short-video generator from a topic (trending Chinese tool)

Registry data updated: 2026-11-16

Config & data

Config file written to

~/AppData/Local/MoneyPrinterTurbo/config.toml

  • ~/AppData/Local/MoneyPrinterTurbo

Everything stays on your own machine — nothing is uploaded. To uninstall, delete these folders.

Install in three steps

  1. 01

    Install AiBOX

    One portable file for Windows (macOS coming). Double-click and it runs — no installer, no administrator rights.

    Go to download →
  2. 02

    Pick MoneyPrinterTurbo

    Open the AiBOX app catalog, find MoneyPrinterTurbo and press Install. AiBOX checks what your machine already has and installs only what is missing.

  3. 03

    Follow the wizard

    It downloads with a checksum check, writes the config and fills in your API key if the app needs one. You just click.

    ✓ Installed until it works.

Prefer to do it by hand? The full written guide is right below. Read the guide ↓

Install guide

The same steps in written form — follow along at your own pace.

One line: MoneyPrinterTurbo turns a single topic into a finished short video — AI writes the script, grabs stock footage, narrates it, burns in subtitles and renders the final cut. The Windows portable build is double-click to run.

What you get

  • Full pipeline from one sentence: script → footage → voice-over → subtitles → edited final video
  • Four ways to drive it: the WebUI, an API server, a CLI, or an AI agent call
  • Free building blocks: Pexels / Pixabay stock footage, plus Edge TTS narration that needs no key at all

Before you start (3 minutes)

NeedNotes
Windows 10/11 x64The portable bundle ships its own runtime — no Python install needed (macOS goes the source route, Python 3.11+)
7-ZipThe bundle is a .7z; grab the free build from 7-zip.org (extracting needs no admin rights)
Disk~2GB (555MB download plus the extracted runtime and caches)
API keyAt least one LLM key for script writing; footage and narration can stay free
PermissionsZero admin — it unpacks into a user folder
⚠️ Path rule (stated by the project): the install path must contain no Chinese characters, spaces or special characters. If your Windows user name is non-ASCII (which poisons C:\Users\<name>\...), unpack to a plain-ASCII folder such as D:\Apps\MoneyPrinterTurbo.

Install

Route A: install with AiBOX (recommended)

  1. Open AiBOX → app directory → MoneyPrinterTurbo → Install
  2. It downloads the 555MB official portable build (CN traffic switches gateway automatically), verifies the hash and extracts into %LOCALAPPDATA%\MoneyPrinterTurbo
  3. Launch from AiBOX or the extracted folder — if your user name contains non-ASCII characters, move it to a plain-ASCII path as noted above

Route B: manual install (official portable build)

  1. Open the Releases page and download MoneyPrinterTurbo-Portable-Windows-1.3.10.7z from the Assets section

(Don't grab GitHub's auto-generated Source code (zip/tar.gz) — that's just the source tree, with no launcher in it)

  1. Right-click the .7z → 7-Zip → Extract Here, or extract to a plain-ASCII folder (e.g. D:\Apps\MoneyPrinterTurbo)
  2. Run MoneyPrinterTurbo.exe; if the archive instead contains start.bat, double-click update.bat first to pull the latest code, then start.bat

First-time configuration, step by step

Fill the settings page in this order and you'll avoid most dead ends:

  1. LLM (script writing): llm_provider defaults to moonshot (Kimi); OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Alibaba Tongyi, iFlytek Spark, local Ollama and any OpenAI-compatible gateway also work — pick one and paste its key
  2. Video footage source: defaults to pexels; get a free key at Pexels API or Pixabay (multiple keys rotate). You can also upload your own clips, or switch to paid AI text-to-video sources
  3. Voice-over (TTS): start with Edge TTS — free, no key required; audition voices and pick one. Upgrade later to Azure / SiliconFlow / ElevenLabs if you want richer voices (platform key needed)
  4. Subtitles: default edge uses the TTS timestamps — fast, no GPU, no downloads. Switch to whisper (local faster-whisper, first use pulls a 1.6–3GB model) for tighter timing
  5. Aspect ratio: 9:16 vertical (TikTok/Shorts/Reels), 16:9 landscape, or 1:1 square

Generation flow, stage by stage

  1. Type a topic on the home screen (one line is enough — or paste your own script)
  2. Hit Generate and watch the staged progress: script → footage download/processing → narration → subtitles → final render
  3. Open any stage while it runs: edit the script and rerun, audition the whole narration track
  4. Preview and download the finished video from task history; batch mode renders several videos in one go

Headless / automation (source deployments):

python cli.py --video-subject "How AI changes everyday life"
python cli.py --help    # full parameter list

There's also an API server: python main.py, with docs at http://127.0.0.1:8080/docs.

Verification: what "success" looks like

  1. The launcher opens the WebUI automatically (blank page? open the URL shown in the terminal — default http://127.0.0.1:8501 — in Chrome or Edge)
  2. Settings show the LLM key filled in and the footage key validated
  3. Run one topic with default settings and get a playable video within minutes

Cost notes

  • Free stack: Pexels/Pixabay footage + Edge TTS narration + edge subtitles → you only pay LLM tokens (a 60-second script usually costs fractions of a cent)
  • Skip paid add-ons at first: AI text-to-video footage sources (Seedance, LoomLoom, …) bill per generation — new users should stay on free stock footage
  • Whisper subtitles run locally for free; you only download the model once (grab it manually into models\whisper-large-v3 if the download stalls)

FAQ

  • Extraction fails / .7z won't open: install 7-Zip first; extraction needs no admin, but the destination must be free of Chinese characters and spaces
  • RuntimeError: No ffmpeg exe could be found: ffmpeg is normally downloaded automatically; if that fails, grab it from gyan.dev and point ffmpeg_path in config.toml at it
  • Whisper model won't download: fetch whisper-large-v3 manually from Hugging Face and unpack it to .\MoneyPrinterTurbo\models\whisper-large-v3
  • Blank page after launch: open the URL printed in the terminal with Chrome or Edge
  • Generation is slow: the bottleneck is usually the cloud LLM/footage API; for local transcription or heavy batch work, a GPU with 4GB+ VRAM helps

Uninstall

# Exit the app first, then delete the folder (drafts, config and task history all live there — back it up!)
Remove-Item -Recurse "$env:LOCALAPPDATA\MoneyPrinterTurbo"

AiBOX's Manage → Uninstall does it for you.

More: GitHub README · Releases

Model / API key setup

AiBOX fills this in for you during the wizard — this section is for setting it up by hand.

Anthropic (Claude)

You need an API key from the provider.

~/AppData/Local/MoneyPrinterTurbo/config.toml

Get a key ↗

OpenAI

You need an API key from the provider.

~/AppData/Local/MoneyPrinterTurbo/config.toml

Get a key ↗

OpenRouter

You need an API key from the provider.

~/AppData/Local/MoneyPrinterTurbo/config.toml

Get a key ↗

Ollama (local)

Local model — no API key needed.

~/AppData/Local/MoneyPrinterTurbo/config.toml

Common questions

Which platforms does MoneyPrinterTurbo run on?

Runs on Windows — install it with AiBOX on any of them.

How hard is MoneyPrinterTurbo to install?

Difficulty 3 out of 5. AiBOX does the download and setup; your part is clicking through the wizard and pasting a key if the app needs one.

Where does MoneyPrinterTurbo keep my data?

Everything stays on your own machine: ~/AppData/Local/MoneyPrinterTurbo. To uninstall, delete these — nothing is ever uploaded.

Something not working?

An outdated step, an error you do not understand, a typo — tell us and we will fix this page.

Report a problem →

Version & updates

Current version
v1.3.10
Registry data updated
2026-11-16

Version numbers are re-checked by our daily probe — when upstream ships a new release, this page follows.

Questions or problems?

A wrong step, a confusing error, a typo — open an issue and someone will look.