MCP Transcribe Online Vids

🚀 MCP Online Video Transcription

A FastMCP-based server that enables large language models (LLMs) to access and transcribe online videos from YouTube and Bilibili, using Replicate and 0x0.st for temporary file hosting.

🚀 Quick Start

This server allows LLMs to transcribe online videos from YouTube and Bilibili. It uses Replicate and 0x0.st for temporary file hosting, providing a convenient way to handle video transcription tasks.

✨ Features

• Transcribe YouTube/Bilibili videos with timestamp output.
• Automatically extract audio and convert formats.
• Perform cloud transcription via the WhisperX model.
• Provide temporary file hosting for large files.

📦 Installation

Prerequisites

• Python 3.12+
• Conda (recommended for environment management)

Environment Setup

# Create and activate a conda environment
conda create --name mcp_transcribe_online_vids python=3.12
conda activate mcp_transcribe_online_vids

# Install required system packages
conda install conda-forge::uv conda-forge::ffmpeg conda-forge::sqlite

# Install Python dependencies
uv pip install -r requirements.txt

Configuration

1. Copy the .env.template file to .env:

   cp .env.template .env
   

2. Edit the .env file with your credentials:
   • REPLICATE_API_TOKEN: Obtain from Replicate's API key page.
   • ZERO_X_URL: The URL of your 0x0.st instance (default is the public instance).
   • TEMP_FILE_PATH: The directory for temporary files.
   • LOCAL_FILE_SIZE_LIMIT: The maximum file size (in MB) for direct upload to the API.

💻 Usage Examples

Starting the Server

python main.py

Available Tools

• get_youtube_transcript(url): Transcribe a YouTube video.
• get_bilibili_transcript(url): Transcribe a Bilibili video.

Basic Usage

from fastmcp import MCPClient
import asyncio

async def get_transcript():
    client = MCPClient("http://localhost:8000")
    async with client:
        transcript = await client.call_tool("get_youtube_transcript",
            {"url": "https://www.youtube.com/watch?v=dQw********"})
        print(transcript)

# Run the asynchronous function
asyncio.run(get_transcript())

📚 Documentation

Deployment Options

For production environment deployment, refer to FastMCP Transport Options. To customize the transport, modify the mcp.run() call in main.py.

Self-hosted File Storage

It is highly recommended to set up your own 0x0.st instance for file storage. Configure your instance according to the Hosting Instructions.

Roadmap

• [ ] Add tools to retrieve video metadata (title, date, description).
• [ ] Add YAML deployment configuration.
• [ ] Increase more file storage options (Google Cloud, S3).
• [ ] Complete the local transcription function using WhisperX.
• [ ] Support other media sources, such as Spotify podcasts.

Contribution Guidelines

For information on how to contribute to the project, refer to the Contributing section.

📄 License

[Project license information]

Contact

• Project Homepage: [https://github.com/your-repository]
• Author's Email: [Your email address]