Video Transcribe MCP

🚀 Video Transcription MCP Server

An MCP server implementation integrated with Optivus, providing video transcription capabilities for large language models (LLMs) (e.g., YouTube, Facebook, TikTok, etc.).

🚀 Quick Start

Using with Dive Desktop

1. Click "+ Add MCP Server" in Dive Desktop.
2. Copy and paste the following configuration:

{
  "mcpServers": {
    "video-transcribe": {
      "command": "npx",
      "args": [
        "-y",
        "@demon24ru/video-transcribe-mcp"
      ]
    }
  }
}

3. Click "Save" to install the MCP server.

Manual Startup

If necessary, you can start the server manually:

npx @demon24ru/video-transcribe-mcp

Debugging

If needed, start the server in debug mode:

npm run prepare
npx @modelcontextprotocol/inspector node ./lib/index.mjs -y

✨ Features

• Video Transcription: Convert videos into text.
• MCP Integration: Use with Dive and other compatible LLMs.

📚 Documentation

API Documentation

• transcribe_video

  • Transcribe a video into text.
  • Input:
    • urls (string, required): The URL of the video.

• transcribe_video_file

  • Transcribe a video file into text.
  • Input:
    • file_path (string, required): The path of the video file.

• transcribe_image

  • Transcribe an image into text.
  • Input:
    • file_path (string, required): The path of the image file.

💻 Usage Examples

Ask your LLM to perform the following operations:

"Transcribe this video: https://youtube.com/watch?v=..."
"Transcribe this video file: /path/to/video.mp4"
"Transcribe this image: /path/to/image.jpg"

📦 Installation

Requirements

• Node.js version 20+
• Compatible LLM service

📄 License

MIT

👨‍💻 Author

@demon24ru