Video to Text

Downloads videos or audio URLs, extracts audio, and transcribes speech to text using OpenAI Whisper with multiple output formats.

typescript

0

GitHub Stars

typescript

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "strzhao-video-to-text-mcp": {
      "command": "node",
      "args": [
        "/path/to/video-to-text-mcp/build/index.js"
      ],
      "env": {
        "TEMP_DIR": "/tmp",
        "WHISPER_MODEL": "base"
      }
    }
  }
}

You can run the Video to Text MCP Server to automatically download videos, extract audio, and transcribe speech into text using OpenAI Whisper. This server supports multiple output formats and can process both video URLs and direct audio URLs, returning the transcription and the local file path.

How to use

Use an MCP client to interact with the Video to Text MCP Server. You will have two tools available: video_to_text for videos and voice_to_text for direct audio URLs. Provide the source URL, choose an output format, and select a language if needed. The server will return a preview of the transcription and the full local path to the transcription file.

How to install

Prerequisites: Node.js and npm, Python 3.8+ for Whisper integration, and network access.

# 1) Install Node.js and npm if not already installed
# 2) Clone or copy the project to your environment
# 3) Install dependencies and build
cd video-to-text-mcp
npm install
npm run build

Additional sections

Configuration and runtime details are shown below. The MCP server runs as a local process via Node.js and accepts environment variables to control Whisper behavior and temporary file handling.

Environment variables shown in the example are optional but recommended for controlling the Whisper model and storage behavior.

{
  "mcpServers": {
    "video_to_text": {
      "command": "node",
      "args": ["/path/to/video-to-text-mcp/build/index.js"],
      "env": {
        "WHISPER_MODEL": "base"
      }
    }
  }
}

Troubleshooting and notes

Common issues include missing tools, such as yt-dlp, ffmpeg, or Whisper. Ensure each dependency is installed and available in your system PATH. Temporary files are created during processing and are stored in the system temporary directory until cleanup.

Available tools

video_to_text

Downloads a video from a supported platform, extracts audio, and transcribes it into text in the requested format and language.

voice_to_text

Downloads audio from a direct URL and transcribes it into text in the requested format and language.