Mcp Video2text
About
Convert online video to text, read it quickly
Details
- Author
- yanyaoer
- GitHub stars
- 2
- Downloads
- 315
- Categories
- Other
Jump to
- Downloads online videos using yt-dlp
- Transcribes audio to text with Whisper models
- Supports MLX backend for Apple Silicon
- Supports C++ backend (whisper.cpp)
- Works with any MCP-compatible client
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 Video2textCommand (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
Install the uv package manager and ffmpeg, then run uv pip install mcp-video2text[mlx] (recommended for Apple Silicon) or uv pip install mcp-video2text[cpp]. In your MCP client configuration, set the command to uv run mcp-video2text. The first execution downloads the Whisper model, which may take a few minutes; adjust your client’s timeout accordingly.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp video2text": {
"mcp-video2text": {
"command": "uv",
"args": [
"run",
"mcp-video2text"
]
}
}
}
}McpServers
{
"mcp-video2text": {
"command": "uv",
"args": [
"run",
"mcp-video2text"
]
}
}mcp-video2text
Convert online video to text, read it quickly
Usage
## require
$ curl -LsSf https://astral.sh/uv/install.sh | sh # install uv package manager
$ brew install ffmpeg # or sudo apt install ffmpeg for linux
install
$ uv pip install mcp-video2text[mlx] # recommend with mlx for silicon machine
$ uv pip install mcp-video2text[cpp]
for mcp client, pass uv run mpc-video2text to command field.
{
"mcpServers": {
"mcp-video2text": {
"command": "uv",
"args": ["run", "mcp-video2text"],
}
}
}
The first run will download the Whisper model and may take a few minutes.
It's recommended to update the timeout settings in your client.
or your can custom your own client, view example test_mcp_client.py
import asyncio
import os
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
async def client():
server_params = StdioServerParameters(
command="uv", args=["run", "mcp-video2text"], env=os.environ
)
async with stdio_client(server_params) as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
print(await session.list_tools())
result = await session.call_tool(
"video2text", {"url": "https://www.bilibili.com/video/BV1gdERzuEYB/"}
)
print(result.content[0].text)
if __name__ == "__main__":
asyncio.run(client())
Thanks
- https://github.com/yt-dlp/yt-dlp - https://github.com/k2-fsa/sherpa-onnx - https://github.com/ml-explore/mlx-examples/tree/main/whisper - https://github.com/ggerganov/whisper.cpp - https://github.com/absadiki/pywhispercpp - https://github.com/pydantic/pydantic-ai - https://github.com/yetone/avante.nvimSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
