### Automated Environment Setup and Execution

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

This guide covers the automated setup of the MoneyPrinterPlus environment and its automatic execution. It simplifies the process of getting the project running and operational.

```APIDOC
Automated Environment Setup and Execution:
  Description: Provides instructions for automatically setting up the MoneyPrinterPlus environment and running the project.
  Usage Guide: https://mp.weixin.qq.com/s/k3B08ol1GJVi2EIyfCgWAg
```

--------------------------------

### Automatic Installation Script

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Executes the setup script for automatic installation. Use setup.bat on Windows or bash setup.sh on macOS/Linux.

```bash
bash setup.sh
```

--------------------------------

### Installation and Running

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Provides instructions for installing and running the MoneyPrinterPlus application, including manual installation via pip and automated scripts for Windows, macOS, and Linux.

```bash
pip install -r requirements.txt
```

```bash
setup.bat
```

```bash
bash setup.sh
```

```bash
streamlit run gui.py
```

```bash
start.bat
```

```bash
bash start.sh
```

--------------------------------

### Automatic Installation (Windows)

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Executes a batch script for automatic installation on Windows systems. This simplifies the setup process.

```bash
setup.bat
```

--------------------------------

### Manual Installation

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Installs project dependencies using pip. Ensure Python 3.10+ and ffmpeg 6.0+ are installed and added to your PATH.

```bash
pip install -r requirements.txt
```

--------------------------------

### Video Clip Resource Directory Example

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Example of placing video clip resources in a directory for batch video mixing.

```Bash
#!/bin/bash
そして、衣服のパターン素材をビデオクリップ1のリソースディレクトリに配置します。

たとえば、上図のリソースディレクトリに：

d:\downloads\work\scen1
```

--------------------------------

### Run Streamlit Application

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Starts the Streamlit web application for the MoneyPrinterPlus project. This command assumes Streamlit is installed and the gui.py file exists in the current directory.

```bash
streamlit run gui.py
```

--------------------------------

### Automatic Installation (Mac/Linux)

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Executes a shell script for automatic installation on macOS and Linux systems. This simplifies the setup process.

```bash
bash setup.sh
```

--------------------------------

### Install Dependencies

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Installs the necessary Python packages for the project using a requirements file. Ensure you have Python 3.10+ and pip installed.

```bash
pip install -r requirements.txt
```

--------------------------------

### Running the Application

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Launches the Streamlit application. This command starts the user interface for MoneyPrinterPlus.

```bash
streamlit run gui.py
```

--------------------------------

### Starting MoneyPrinterPlus

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Instructions for launching the MoneyPrinterPlus application on different operating systems. Double-click 'start.bat' on Windows or execute 'sh start.sh' in the project root on Mac.

```batch
start.bat
```

```shell
sh start.sh
```

--------------------------------

### Batch Video Editing Setup

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Explains the setup for batch video editing, allowing configuration of up to 5 video segments. Each segment can have its own media resources and text descriptions.

```APIDOC
Batch Video Editing Setup:
  - Access: Video Mixing section in the top-left corner.
  - Segment Configuration: Up to 5 video segments can be configured.
  - Segment Management: Add or delete segment areas.
  - Video Segment Definition:
    - A segment represents a part of a long video with a specific theme.
    - Media Resources: Can be MP4 videos, JPG, or PNG images. Higher resolution is recommended.
    - Resource Directory Example: `d:\downloads\work\scen1`
  - Video Resource Text Description:
    - Text files (.txt) containing descriptions for each segment.
    - Each line in the .txt file is a potential description.
    - System randomly selects one description per segment.
```

--------------------------------

### Video Resource Text Description Example

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Provides an example of a text file containing multiple descriptions for a video segment, where each line represents a different textual description.

```txt
精准的剪裁，流畅的线条，这款马甲的版型设计，完美贴合身形，无论是宽松还是修身，都能展现你的优雅姿态。
我们的设计师们，将经典与现代完美融合。每一道线条，每一个剪裁，都是为了展现你的独特身形。
每一刀剪裁，都经过精心计算，只为打造最适合你身形的版型。从肩部线条到腰部剪裁，每一处都彰显着你的独特风格。
精准的剪裁，流畅的线条，这款马甲的版型设计，旨在让每一位穿着者都能感受到定制般的贴合。
精准剪裁流畅线条，马甲版型设计完美贴合身形，宽松或修身皆展现优雅姿态。
设计师将经典与现代融合，每道线条每个剪裁展现独特身形。
精心计算每一刀剪裁，打造适合身形的版型，肩部线条至腰部剪裁彰显独特风格。
剪裁精准流畅，马甲版型旨在定制般贴合，展现穿着者个性魅力。
面料精选剪裁精致，马甲版型以优雅线条展现身形，正式或休闲皆完美。
人体工学设计，马甲版型舒适透气，优雅线条展现身形，每次穿搭成焦点。
经典版型现代演绎，马甲独特剪裁设计，穿着成展现个性品味舞台。
细节精心打磨，马甲版型合体剪裁精致细节，任何场合自信满满。
舒适型格并存，马甲版型精致剪裁舒适面料，工作休闲展现最佳状态。
时尚马甲版型多样，每款为你而生，经典剪裁现代设计，轻松驾驭各种风格。
优雅线条修身设计，马甲版型考究剪裁精致细节，任何场合成焦点，彰显个人风格。
```

--------------------------------

### Video Segment Resource Directory Example

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

This example shows the directory structure for storing resources for a specific video segment. High-resolution images (JPG, PNG) or video files (MP4) should be placed here.

```bash
d:\\downloads\\work\\scen1
```

--------------------------------

### Video Document File Example

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Example of a text file containing multiple descriptions for a video clip, where each description is on a new line.

```Text
正確なカット、滑らかなライン、このベストのデザインは、完璧にフィットし、ゆったりとしたスリムなどのユニークなスタイルを示すことができます。
デザイナーは、クラシックと現代を完璧に融合させました。すべてのライン、すべてのカットは、あなたのユニークな体型を表現するためにあります。
すべてのカットは、慎重に計算され、あなたの体型に最適なデザインを作るために行われます。肩のラインからウエストのカットまで、すべてがあなたのユニークなスタイルを示しています。
正確なカット、滑らかなライン、このベストのデザインは、すべての着用者がカスタムメイドのようにフィットすることを目指しています。
正確なカット、滑らかなライン、このベストのデザインは、すべての着用者がカスタムメイドのようにフィットすることを目指しています。
デザイナーは、クラシックと現代を完璧に融合させました。すべてのライン、すべてのカットは、あなたのユニークな体型を表現するためにあります。
すべてのカットは、慎重に計算され、あなたの体型に最適なデザインを作るために行われます。肩のラインからウエストのカットまで、すべてがあなたのユニークなスタイルを示しています。
正確なカット、滑らかなライン、このベストのデザインは、すべての着用者がカスタムメイドのようにフィットすることを目指しています。
面料の選択、精巧なカット、ベストのデザインは、優雅なラインで体型を表現し、フォーマルな場面からカジュアルな場面まで完璧です。
人間工学に基づいたデザイン、ベストのデザインは、快適で通気性があり、優雅なラインで体型を表現し、毎回着用するたびに焦点になります。
あなたの個性的な味を示す独特なカットデザイン、ベストのデザインは、細部にこだわり、自信に満ちたデザインです。
快適さとスタイルの両立、ベストのデザインは、精巧なカットと快適な生地で、仕事場でも休日でも最適な状態を示します。
スタイリッシュなベストデザインの多様性、すべてはあなたのために作られており、クラシックなデザインとモダンなデザインが、さまざまなスタイルを楽に乗りこなすことができます。
優雅なラインとスリムなデザイン、ベストのデザインは、洗練されたディテールと繊細なカットを表現し、どんな場面でも個人のスタイルを示します。
```

--------------------------------

### MoneyPrinterPlus Video Tutorials

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

A collection of video tutorials covering the introduction, detailed usage, batch generation, and beginner's guide to MoneyPrinterPlus. These videos demonstrate the capabilities of the AI short video generation tool.

```Video
https://www.bilibili.com/video/BV16VVGefEp1/?spm_id_from=333.999.0.0&vd_source=a563b6c970df6e7665845c15089bd618
```

```Video
https://www.bilibili.com/video/BV1JKgYe5ERF/?pop_share=1&vd_source=a563b6c970df6e7665845c15089bd618
```

```Video
https://www.bilibili.com/video/BV1v43eekECn/?spm_id_from=333.999.0.0&vd_source=a563b6c970df6e7665845c15089bd618
```

```Video
https://www.bilibili.com/video/BV1XgaKeGEFb/
```

--------------------------------

### Video Segment Text Resource Example

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

This example demonstrates the format for text files used for video segment descriptions. Each line in the .txt file represents a distinct textual description that the system can randomly select.

```txt
Accurate cutting, smooth lines, the design of this vest perfectly fits the body shape, whether it is loose or slim, it can show your elegant posture.
Our designers perfectly blend classic and modern styles. Every line and every cut is to showcase your unique body shape.
Every precise cut is carefully calculated to create the most suitable style for your body. From the shoulder line to the waist cut, each part showcases your unique style.
Accurate cutting, smooth lines, the design of this vest is intended to make every wearer feel the tailored fit.
Accurate cutting, smooth lines, the design of this vest fits perfectly, showing elegant posture whether it's loose or slim.
Designers blend classic and modern styles, every line and cut showcases a unique body shape.
Every precise cut is carefully calculated to create a style that suits your body shape, showcasing a unique style from the shoulder line to the waist cut.
Accurate cutting and smooth lines, the vest design is aimed at a tailored fit, showcasing the wearer's personal charm.
```

--------------------------------

### Automatic Execution (Windows)

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Starts the application automatically on Windows by double-clicking the start.bat file. Logs are available in a log file.

```bash
start.bat
```

--------------------------------

### Automatic Execution (Mac/Linux)

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Starts the application automatically on macOS and Linux using a shell script. Logs are available in a log file.

```bash
bash start.sh
```

--------------------------------

### Batch Video Mixing Setup

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Configure batch video mixing by adding and removing up to 5 video clips. Each clip can be composed of video or image resources.

```Japanese
プロジェクトを起動した後、左上隅にビデオミックスエリアがあります。
それをクリックして、バッチビデオミックスツールページに入ることができます。
ビデオミックスエリアでは、最大で5つのビデオクリップを構成できます。
ビデオクリップを追加したり削除したりして、クリップエリアを制御できます。
```

--------------------------------

### Firefox Debug Mode Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Instructions for starting the Firefox browser in remote debugging mode using the marionette debugger server. This requires a specific command-line argument and uses a fixed port.

```bash
firefox -marionette -start-debugger-server 2828
```

--------------------------------

### Chrome Debug Mode Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Instructions for starting the Chrome browser in remote debugging mode, essential for automation tools like MoneyPrinterPlus. This involves setting a specific port for communication.

```bash
alias chrome="/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome"
chrome --remote-debugging-port=9222
```

--------------------------------

### Batch Video Generation

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Generate up to 100 videos in a single batch. Click the 'Generate Video' button to start. Progress is displayed on the page. Generated videos are found in the 'final' directory.

```Japanese
最後にビデオを生成ボタンをクリックしてビデオを生成できます。
ページには対応する進捗状況が表示されます。
最後に生成されたビデオは、ページの一番下に表示されます。お好きなように再生できます。
複数のビデオを生成した場合は、プロジェクトフォルダのfinalディレクトリで生成したビデオを見つけることができます。
```

--------------------------------

### Video Configuration Options

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Set video layout, frame rate, size, and enable transition effects. Supports over 30 transition effects.

```APIDOC
VideoLayoutConfig:
  layout: str
  frame_rate: int
  video_size: tuple[int, int]
  enable_transitions: bool
  transition_type: str (optional)
```

--------------------------------

### Resource and Audio Library Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Explains how to configure resource libraries (Pexels, Pixabay) and audio libraries (Azure, Alibaba Cloud, Tencent Cloud) for video content and voice processing.

```APIDOC
Resource Libraries:
  Pexels: Free stock photos and videos. Requires API key from www.pexels.com.
  Pixabay: Free stock photos and videos. Requires API key from pixabay.com.
  Future additions: videvo.net, videezy.com.

Audio Libraries (Text-to-Speech and Speech Recognition):
  Azure:
    - Service: Cognitive Services.
    - Key Acquisition: https://speech.microsoft.com/portal
  Alibaba Cloud:
    - Service: Intelligent Speech Interaction.
    - Key Acquisition: https://nls-portal.console.aliyun.com/overview
    - Required Features: Speech Synthesis, Recording File Recognition (UltraFast).
  Tencent Cloud:
    - Service: Speech Recognition and Speech Synthesis.
    - Key Acquisition: https://console.cloud.tencent.com/asr
```

--------------------------------

### Video Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Covers video configuration settings including layout, frame rate, resolution, clip length, and transition effects. It mentions support for over 30 transition effects and a future feature for using local video resources.

```APIDOC
Video Configuration:
  Settings:
    - Layout (Portrait, Landscape, Square)
    - Frame Rate
    - Resolution
    - Minimum Clip Length
    - Maximum Clip Length
    - Transition Effects (30+ supported)
  Upcoming Feature:
    - Use local video resources
```

--------------------------------

### Supported LLMs and API Endpoints

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Lists the Large Language Models (LLMs) supported by MoneyPrinterPlus and provides their respective API acquisition URLs. It recommends using Moonshot and mentions that other popular LLMs will be added.

```APIDOC
LLM Support:
  - Moonshot: https://platform.moonshot.cn/
  - OpenAI
  - Azure OpenAI
  - Baidu Qianfan: https://cloud.baidu.com/doc/WENXINWORKSHOP/s/yloieb01t
  - Baichuan: https://www.baichuan-ai.com/
  - Tongyi Qwen: https://help.aliyun.com/document_detail/611472.html?spm=a2c4g.2399481.0.0
  - DeepSeek: https://www.deepseek.com/

Recommendation: Moonshot
```

--------------------------------

### Project Execution Scripts

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Commands to execute the MoneyPrinterPlus project on different operating systems. This includes running a batch file on Windows and a shell script on macOS.

```bash
windows环境下，直接双击start.bat即可启动。
mac环境下，在项目根目录下面执行sh start.sh即可。
```

--------------------------------

### Automatic Running Script

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Executes the script to automatically run the application. Use start.bat on Windows or bash start.sh on macOS/Linux.

```bash
bash start.sh
```

--------------------------------

### Batch Video Uploading - Working Principle

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Explains that the automatic publishing tool uses the Selenium automation framework to simulate user actions. It operates by attaching to an existing browser session to handle tasks that are difficult to automate, such as QR code logins.

```APIDOC
Automatic Publishing Tool:
  Framework: Selenium
  Method: Simulates human click operations.
  Operation Mode: Attaches to an existing browser session.
  Reasoning for Mode: To handle complex logins like QR code scanning, which are difficult to automate programmatically.
```

--------------------------------

### Resource Library and Video Features

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Details on supported resource library integrations and video manipulation features, including transitions and background music.

```APIDOC
Resource Library and Video Features:
  Functionality: Manages video resources and applies various effects.
  Resource Library Support:
    - Pixabay integration
  Video Features:
    - Supports local material selection (mp4, jpg, png)
    - Supports various resolutions
    - Supports 30+ video transition effects
    - Supports background music
    - Supports background music volume adjustment
    - Supports custom subtitles
    - Supports video generation in different resolutions, sizes, and proportions
```

--------------------------------

### Cloud and SDK Dependencies

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/requirements.txt

Lists SDKs for cloud services, including Alibaba Cloud Core, Tencent Cloud TTS, and Qianfan.

```python
qianfan==0.3.15
aliyun-python-sdk-core==2.15.1
tencentcloud-sdk-python-tts==3.0.1168
```

--------------------------------

### Video Settings Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Set video layout, frame rate, and size. Configure minimum and maximum video clip lengths and apply over 30 transition effects.

```Japanese
ビデオのレイアウト、フレームレート、サイズを選択できます。
ビデオクリップの最小長と最大長を設定できます。
また、30以上のトランジション効果を適用することもできます。
```

--------------------------------

### Speech Recognition and Synthesis Support

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

The tool supports speech recognition and synthesis functionalities, with specific integrations for Tencent Cloud and Alibaba Cloud services.

```APIDOC
Speech Recognition and Synthesis Support:
  Functionality: Enables speech recognition and synthesis for video content.
  Supported Cloud Services:
    - Tencent Cloud:
        - Requires enabling Tencent Cloud's speech synthesis and speech recognition functions.
    - Alibaba Cloud:
        - Requires enabling Alibaba Cloud's Intelligent Speech Interaction feature.
        - Must enable speech synthesis and recording file recognition (Express Edition) functions.
  Features:
    - Supports 100+ different voice types
    - Supports voice preview function
    - Supports voice selection and speed adjustment
```

--------------------------------

### Batch Video Uploading - Prerequisites

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

States the browser prerequisites for the automatic publishing tool, specifying support for Chrome and Firefox.

```APIDOC
Automatic Publishing Tool Prerequisites:
  Supported Browsers:
    - Chrome
    - Firefox
  User Choice: Select one browser as needed.
```

--------------------------------

### Voiceover and Background Music Settings

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Customize voiceover by selecting language and voice, and adjusting speed. Background music can be added from the 'bgmusic' folder.

```APIDOC
AudioConfig:
  voiceover_language: str
  voiceover_voice: str
  voiceover_speed: float
  background_music_path: str
```

--------------------------------

### Batch Video Automatic Upload Tool

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

This tool automates the publishing of short videos to multiple platforms including Douyin, Kwai, Xiaohongshu, and Video Number. It supports various cloud voice features.

```APIDOC
Batch Video Automatic Upload Tool:
  Functionality: Automatic publishing of short videos to multiple platforms.
  Supported Platforms: Douyin, Kwai, Xiaohongshu, Video Number.
  Features:
    - One-click publishing
    - Supports Azure voice features
    - Supports Alibaba Cloud voice features
    - Supports Tencent Cloud voice features
    - Supports 100+ different voice types
    - Supports voice preview function
    - Supports voice selection and speed adjustment
    - Supports background music and volume adjustment
  Usage Tutorial: [MoneyPrinterPlus One-Click Publishing of Short Videos to Video Number, Douyin, Kwai, and Xiaohongshu Is Now Live](https://mp.weixin.qq.com/s/QOpSbb_q01E0CWAI3KQ89w)
```

--------------------------------

### Download and Prepare Sense Voice Model

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/sensevoice/README.md

This snippet demonstrates how to download the sense voice model for multiple languages (Chinese, English, Japanese, Korean, Cantonese) using curl and then extract the archive using tar. It also includes removing the downloaded archive after extraction.

```shell
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
tar xvf sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
rm sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
```

--------------------------------

### Audio Processing and Utilities

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/requirements.txt

Details libraries for audio manipulation (pydub, pyaudio) and system utilities (psutil), along with a high-performance Whisper implementation.

```python
pydub
psutil
pyaudio
faster-whisper==1.0.3
```

--------------------------------

### Resolving chatTTS 'fbgemm.dll' Loading Error

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/issue.md

The chatTTS error 'Error loading \site-packages\torch\lib\fbgemm.dll" or one of its dependencies' is due to missing dependencies for torch, specifically 'libomp140.x86-64'. Download the required DLL and place it in the C:\Windows\System32 folder.

```en
Error loading \site-packages\torch\lib\fbgemm.dll" or one of its dependencies.
```

--------------------------------

### Subtitle Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Configure subtitle appearance including position, color, border color, and border width. Supports Songti and Pingfang font collections.

```APIDOC
SubtitleConfig:
  font_collection: str ('Songti' or 'Pingfang')
  position: str
  color: str
  border_color: str
  border_width: int
```

--------------------------------

### AI Video Batch Mixing Tool

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

This tool allows for the batch mixing of short videos using AI technology. It is designed to streamline the process of combining multiple video clips into a cohesive output. Detailed usage instructions are available.

```APIDOC
AI Video Batch Mixing Tool:
  Description: Batch mixes short videos using AI technology.
  Usage Guide: https://mp.weixin.qq.com/s/gUB18fTwRUvo9dSgk0DXLg
```

--------------------------------

### Cloud and Local Large Model Integration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

MoneyPrinterPlus supports integration with a wide range of cloud-based and local large models for enhanced AI capabilities in video processing.

```APIDOC
Cloud and Local Large Model Integration:
  Functionality: Integration with various AI large models for video processing.
  Supported Cloud Models:
    - OpenAI
    - Azure
    - Kimi
    - Qianfan
    - Baichuan
    - Tongyi Qwen
    - DeepSeek
  Supported Local Models:
    - Ollama
  Features:
    - Covers mainstream AI large model tools on the market.
```

--------------------------------

### Miscellaneous Libraries

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/requirements.txt

Includes other utility libraries like wxPython for GUI development, pyperclip for clipboard interaction, and pybase16384.

```python
wxPython
pyperclip
pybase16384
```

--------------------------------

### Web Development and UI Libraries

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/requirements.txt

This section lists the dependencies for web-based user interfaces and browser automation, specifically Streamlit for UI and Selenium for browser control.

```python
streamlit==1.34.0
selenium==4.20.0
```

--------------------------------

### Automated Short Video Publishing Tool

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

This tool automates the process of publishing short videos to various platforms including Douyin, Kuaishou, Xiaohongshu, and WeChat Channels. It simplifies content distribution for creators.

```Python
import moneyprinterplus

# Example usage for automated video publishing
# Refer to the documentation for detailed parameters and platform configurations.
# moneyprinterplus.publish_video(video_path='path/to/video.mp4', platform='douyin', ...)

```

--------------------------------

### Video Content Generation Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Configure video generation by providing a keyword, selecting language, and duration. The generated content can be manually modified.

```APIDOC
VideoGenerationConfig:
  keyword: str
  language: str
  duration: int
```

--------------------------------

### Video Generation Process

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Generate videos by clicking the 'Generate Video' button. The page displays the process name and progress. Generated videos are displayed at the bottom for playback.

```Japanese
最後に、ビデオの生成をクリックしてビデオを生成できます。
ページには手順名と進捗が表示されます。
ビデオの生成が完了すると、ビデオは下部に表示され、直接再生して確認できます。
```

--------------------------------

### Video Content Text File Format

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Specifies the format for text files accompanying video content. The first line must be the video title, followed by the descriptive content.

```txt
Wang Wei: To Guo Geshi
The high pavilion door is covered in lingering light, with peach and plum trees shading and willow catkins flying.
The sparse bells in the forbidden palace chime late, and the crying birds in the provincial office are rare.
Morning shakes the jade pendants and rushes to the golden palace, while evening offers the heavenly book and bows in the imperial hall.
I want to accompany you without growing old, and I'll lay down my morning attire due to illness.
```

--------------------------------

### MoneyPrinterPlus API Documentation

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

This section outlines the core functionalities and potential API endpoints for MoneyPrinterPlus. It covers AI video generation, batch editing, and automated publishing.

```APIDOC
MoneyPrinterPlus:
  description: A suite of tools for AI-powered short video creation and automation.

  Features:
    - AI Video Generation: Create videos using AI models.
    - Batch Video Editing: Edit multiple videos simultaneously.
    - Automated Publishing: Publish videos to Douyin, Kuaishou, Xiaohongshu, WeChat Channels.

  AI Video Generation:
    generate_video(prompt: str, output_path: str, ai_model: str = 'ollama', **kwargs):
      Generates a video based on a text prompt using a specified AI model.
      Parameters:
        prompt (str): The text prompt to guide video generation.
        output_path (str): The file path to save the generated video.
        ai_model (str): The AI model to use (e.g., 'ollama', 'gpt-sovits').
        **kwargs: Additional model-specific parameters.
      Returns: Path to the generated video file.

  Batch Video Editing:
    batch_edit_videos(input_dir: str, output_dir: str, edit_script: str, ai_model: str = 'gpt-sovits', **kwargs):
      Performs batch editing on videos in a directory based on an editing script.
      Parameters:
        input_dir (str): Directory containing input videos.
        output_dir (str): Directory to save edited videos.
        edit_script (str): Path to the script defining editing operations.
        ai_model (str): The AI model to use for editing (e.g., 'gpt-sovits').
        **kwargs: Additional model-specific parameters.
      Returns: List of paths to edited video files.

  Automated Publishing:
    publish_video(video_path: str, platform: str, **kwargs):
      Publishes a video to a specified platform.
      Parameters:
        video_path (str): Path to the video file to publish.
        platform (str): The target platform (e.g., 'douyin', 'kuaishou', 'xiaohongshu', 'wechat_channels').
        **kwargs: Platform-specific authentication and posting details.
      Returns: Status of the publishing operation.

  Supported AI Models:
    - Ollama
    - GPT-SoVITS
    - chatTTS
    - fasterWhisper

  Supported Platforms:
    - Douyin
    - Kuaishou
    - Xiaohongshu
    - WeChat Channels

```

--------------------------------

### Voiceover and Background Music Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Configure voiceover language, voice, and speed. Background music can be added from the 'bgmusic' folder, and users can add their own music files.

```Japanese
ボイスオーバーの言語と音声を選択できます。
音声の速度調整もサポートされています。
BGMはプロジェクトのbgmusicフォルダに配置されています。
現在、2つのBGMしかありませんが、必要なBGMを自分で追加できます。
```

--------------------------------

### AI Model and Cloud Service Integration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Details the integration with various local AI models (GPTsoVITS, fasterwhisper, ChatTTS, Ollama) and cloud AI services (Azure, Alibaba Cloud, Tencent Cloud) for voice generation, speech recognition, and large language models.

```APIDOC
Local AI Models:
  GPTsoVITS: Supports local GPTsoVITS voice models.
  fasterwhisper: Supports local fasterwhisper speech recognition models.
  ChatTTS: Supports local ChatTTS voice models.
  Ollama: Supports local large language models via Ollama.

Cloud AI Services:
  Azure:
    - Cognitive Services for speech synthesis and recognition.
    - Requires API key from https://speech.microsoft.com/portal.
    - Offers 1 year of free usage for new users.
  Alibaba Cloud:
    - Intelligent Speech Interaction for speech synthesis and recognition.
    - Requires API key and service activation from https://nls-portal.console.aliyun.com/overview.
    - Must enable Speech Synthesis and Recording File Recognition (UltraFast).
  Tencent Cloud:
    - Speech recognition and synthesis services.
    - Requires API key and service activation from https://console.cloud.tencent.com/asr.
    - Must enable Speech Recognition and Speech Synthesis.
```

--------------------------------

### Batch Video Splicing Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

Configure up to 5 video segments for batch splicing. Users can add or delete segments as needed.

```APIDOC
BatchSplicingConfig:
  segments: list[VideoSegment]
  max_segments: int = 5

VideoSegment:
  source_path: str
  start_time: float
  end_time: float
```

--------------------------------

### Video Script Generation

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Explains the process of generating video scripts using LLMs. It involves providing a keyword and configuring script language and duration. Users can also manually modify the generated script.

```APIDOC
Video Script Generation:
  Input: Keyword
  Output: Video script
  Configuration:
    - Script Language
    - Video Duration
  Features:
    - LLM-based script generation
    - Manual script editing
```

--------------------------------

### Video Content Text File Format

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Specifies the format for text files accompanying video content. The first line must be the video title, followed by any additional descriptive text.

```txt
王维：酬郭给事
洞门高阁霭馀辉，桃李阴阴柳絮飞。
禁里疏钟官舍晚，省中啼鸟吏人稀。
晨摇玉佩趋金殿，夕奉天书拜琐闱。
强欲从君无那老，将因卧病解朝衣。
```

--------------------------------

### General Purpose and Networking Libraries

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/requirements.txt

Covers commonly used libraries for general programming tasks, networking, and asynchronous operations.

```python
tenacity==8.3.0
pillow
dashscope
requests
aiohttp
```

--------------------------------

### Subtitle Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Describes subtitle settings, including font selection (Songti, Pingfang), position, color, and border width. Font files are located in the 'fonts' folder.

```APIDOC
Subtitle Configuration:
  Font Location: 'fonts' folder in the project root
  Supported Fonts:
    - Songti
    - Pingfang
  Settings:
    - Subtitle Position
    - Subtitle Color
    - Subtitle Border Color
    - Subtitle Border Width
```

--------------------------------

### Batch Video Auto Upload Tool

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

This tool automates the uploading of short videos to platforms such as TikTok, Kwai, Xiaohongshu, and Video Number. It supports batch uploading, significantly reducing manual effort. Instructions for its use are available.

```APIDOC
Batch Video Auto Upload Tool:
  Description: Automatically uploads videos in batches to TikTok, Kwai, Xiaohongshu, and Video Number.
  Usage Guide: https://mp.weixin.qq.com/s/QOpSbb_q01E0CWAI3KQ89w
```

--------------------------------

### AI Video Generator

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/en/README.md

This tool is designed for generating AI videos. It leverages various cloud and local large models for content creation.

```APIDOC
AI Video Generator:
  Functionality: Generation of AI videos.
  Dependencies: Cloud large model integration (OpenAI, Azure, Kimi, Qianfan, Baichuan, Tongyi Qwen, DeepSeek), Local large model integration (Ollama).
  Features:
    - Supports cloud large model integration
    - Supports local large model integration
  Usage Tutorial: [MoneyPrinterPlus Detailed Usage Tutorial](https://mp.weixin.qq.com/s/fAdws2grcZknG8VLQfjMjg)
```

--------------------------------

### Core LangChain and AI Dependencies

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/requirements.txt

This snippet details the essential LangChain libraries and related AI/ML packages, including OpenAI and Azure Cognitive Services for speech processing.

```python
langchain_openai==0.1.1
langchain==0.1.20
langchain-community==0.0.38
openai==1.16.2
azure-cognitiveservices-speech==1.36.0
```

--------------------------------

### Video Dubbing and Background Music

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Details the options for video dubbing and background music. Users can select voiceover language, voice style, and adjust speech speed. Background music can be added from the 'bgmusic' folder.

```APIDOC
Video Dubbing & Background Music:
  Dubbing Options:
    - Language
    - Voice Style
    - Speech Speed Adjustment
    - Voice Preview (upcoming feature)
  Background Music:
    - Location: 'bgmusic' folder in the project
    - User can add custom music files.
    - Options for enabling background music and setting volume.
```

--------------------------------

### Batch Video Generation Capacity

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Details the system's capacity for batch video generation, stating it supports generating up to 100 videos at once and allows users to adjust this number based on their needs.

```APIDOC
Batch Video Generation:
  Capacity: Up to 100 videos simultaneously.
  Customization: Users can adjust the batch size as required.
```

--------------------------------

### Video Audio Area Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/docs/jp/README.md

Select from over 100 voice languages and corresponding voices. Adjust voice speed for different scenarios and preview audio samples.

```Japanese
ビデオの音声エリアでは、100以上の音声言語と対応する音声言語を選択できます。
さらに、異なる音声速度を選択して、さまざまな使用シーンに対応できます。
音声に自信がない場合は、音声サンプルをクリックして、対応する音声を試聴できます。
```

--------------------------------

### Firefox Debug Mode Configuration

Source: https://github.com/ddean2009/moneyprinterplus/blob/main/README.md

Instructions for launching Mozilla Firefox in debug mode using the marionette protocol. This requires specific command-line arguments to enable remote debugging on a fixed port.

```bash
firefox -marionette -start-debugger-server 2828
```