MCP Transcribe Online Videos
About
A FastMCP server that allows LLMs to access and transcribe online videos from YouTube and Bilibili. It uses Replicate for cloud-based transcription via WhisperX models and 0x0.st for temporary file hosting.
Details
- License
- GPL-3.0 license
Explore
- Transcribe YouTube/ Bilibili videos with timestamped output
- Automatic audio extraction and format conversion
- Cloud-based transcription via WhisperX models
- Temporary file hosting for large files
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Transcribe Online VideosCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.12+
- Conda (recommended for environment management)
conda create --name mcp_transcribe_online_vids python=3.12
conda activate mcp_transcribe_online_vids
conda install conda-forge::uv conda-forge::ffmpeg conda-forge::sqlite
uv pip install -r requirements.txt
For deploying the server in production environments, see FastMCP transport options.
To customize the transport, modify the mcp.run() call in main.py.
- get_youtube_transcript(url): Transcribe a YouTube video
- get_bilibili_transcript(url): Transcribe a Bilibili video
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp transcribe online videos": {
"mcp_transcribe_online_vids": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}
}McpServers
{
"mcp_transcribe_online_vids": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}A FastMCP server that allows LLMs to access and transcribe online videos from YouTube and Bilibili using Replicate and 0x0.st for temporary file hosting.
Features
- Transcribe YouTube/ Bilibili videos with timestamped output
- Automatic audio extraction and format conversion
- Cloud-based transcription via WhisperX models
- Temporary file hosting for large files
Installation
Prerequisites
- Python 3.12+
- Conda (recommended for environment management)
Setting Up the Environment
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
