Transcription MCP Sever
Description
# Transcription MCP Sever An MCP (Model-Context-Protocol) server for transcribing MP3 audio files using the AssemblyAI API. This server provides command-line and Docker-based tools to transcribe audio. this application can be use by Podcasters, Content Creator, Educators and…
About
# Transcription MCP Sever An MCP (Model-Context-Protocol) server for transcribing MP3 audio files using the AssemblyAI API. This server provides command-line and Docker-based tools to transcribe audio. this application can be use by Podcasters, Content Creator, Educators and Business Teams making thier task more…
Details
- Author
- Charisma2595
- Downloads
- 259
- Categories
- Other
Jump to
- Transcribe MP3 audio files into JSON transcripts via AssemblyAI API
- Speaker diarization (speaker labels) enabled
- Saves transcripts in a local "transcripts/" directory
- Accepts file paths via command-line interface (Google Fire)
- Ready to run in a Docker container for portability
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
Transcription MCP SeverCommand (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 dependencies from requirements.txt, set your AssemblyAI API key as the API_KEY environment variable, then run with mcp dev or mcp install to connect with an AI assistant like Claude, or use the provided client script with a file path.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"transcription mcp sever": {
"transcription_mcp_server": {
"command": "uv",
"args": [
"run",
"mcp",
"dev",
"mcpserver_transcription.py"
]
}
}
}
}McpServers
{
"transcription_mcp_server": {
"command": "uv",
"args": [
"run",
"mcp",
"dev",
"mcpserver_transcription.py"
]
}
}Transcription MCP Sever
An MCP (Model-Context-Protocol) server for transcribing MP3 audio files using the AssemblyAI API. This server provides command-line and Docker-based tools to transcribe audio. this application can be use by Podcasters, Content Creator, Educators and Business Teams making thier task more easier.
Features
- Accepts .mp3 files via command-line interface using Fire
- Accepts .mp3 file path provided via an AI assistant such as Claude or Cursor.
- Transcribe MP3 audio files into JSON transcripts using AssemblyAI API
- Speaker diarization (speaker labels) enabled
- Save transcripts in a local "transcripts/" directory
- Easy-to-use command-line interface
- ready to run in a Docker container for portability and deployment
System Architecture Overview
This application is a microservice designed to transcribe audio files using AssemblyAI.
Architecture Breakdown
- Uvicorn as MCP Server Runtime: Uvicorn runs the server process, acting as the entry point for executing transcription jobs. - AssemblyAI Client: This component handles all communication with the AssemblyAI API. - CLI via Google Fire: The application includes a robust command-line interface built with Google Fire. Users can transcribe audio files directly from the terminal - Dockerized Environment: While the server can be run directly on a local machine, it also includes a lightweight Docker configuration for users who prefer containerized deployment.Getting started
Prerequisites
- Python 3.10+ (its Stable, popular, well-supported) - Uvicorn (Lightweight ASGI server ) - Google Fire ( CLI Framework, Makes CLI creation simple and powerful) - AssemblyAI API key (API Interface, sign up at https://www.assemblyai.com/) - Docker (optional, for containerized usage. Ensures consistent, portable deployment)Installation
1. Clone the repository:
git clone <your-repo-url>
cd <repo-folder>
2. Install dependencies:
pip install -r requirements.txt
3. Set your AssemblyAI API key as an environment variable:
export API_KEY="your_assemblyai_api_key" # Linux / macOS
set API_KEY="your_assemblyai_api_key" # Windows CMD
Usage
Inspec With MCP Dev
Run This Command To Inspect And Test The Fuctionality Of Your Tool on a Web Ui.uv run mcp dev mcp\server_transcription.py
connect and test server_transcription
Run the command to connect with claudeuv run mcp install mcp\server_transcription.py
Json Format
when connecting with an AI assitant like claude or cursor, the config should be in this jason format.{
"mcpServers": {
"Audio Transcription Service": {
"command": "C:\\Users\\HomePC\\Desktop\\mcp_task2\\.venv\\Scripts\\uv.EXE",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"C:\\Users\\HomePC\\Desktop\\mcp_task2\\mcp\\server_transcription.py"
],
"env": {
"API_KEY": "<your-api-key-here>"
}
}
}
}
test client_transcription
Run the commandpython mcp\client_transcription.py "path/to/audio/file"
Docker Usage
Build Docker Imagedocker build -t transcription-service -f run_with_docker/Dockerfile .
set API_KEY="your-api-key-here"
docker run -d -p 8050:8050 -e API_KEY=%API_KEY% -v C:\Users:/mnt/users -v %CD%\transcripts:/app/transcripts -v %CD%\logs:/app/logs --dns 8.8.8.8 --name transcription-server transcription-service
run client
python run_with_docker\client.py "path/to/audio/file"
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
