MCP cover image
See in Github
2025-03-12

Model Control Protocol (MCP) server for ElevenLabs Scribe ASR API

1

Github Watches

1

Github Forks

1

Github Stars

ElevenLabs Scribe MCP Server

A Model Control Protocol (MCP) server implementation for ElevenLabs' Scribe speech-to-text API, providing real-time transcription capabilities with advanced context management and bidirectional streaming.

Features

  • Real-time Transcription: Stream audio directly from your microphone and get instant transcriptions
  • File-based Transcription: Upload audio files for batch processing
  • MCP Protocol Support: Full implementation of the Model Control Protocol for better context management
  • WebSocket Support: Real-time bidirectional communication
  • Context Management: Maintain conversation context for improved transcription accuracy
  • Multiple Audio Formats: Support for various audio formats with automatic conversion
  • Language Detection: Automatic language detection and confidence scoring
  • Event Detection: Identify speech and non-speech audio events

Installation

  1. Clone the repository:
git clone https://github.com/aromanstatue/MCP-Elevenlab-Scribe-ASR.git
cd MCP-Elevenlab-Scribe-ASR
  1. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies:
pip install -e .
  1. Create a .env file with your ElevenLabs API key:
ELEVENLABS_API_KEY=your-api-key-here

Usage

Starting the Server

python -m elevenlabs_scribe_mcp_server.main

The server will start on port 8000 by default (or the next available port).

Using the Example Client

  1. File Transcription:
python examples/client_example.py --file path/to/audio.wav
  1. Microphone Transcription:
python examples/client_example.py --mic

API Endpoints

  1. REST API:
  • POST /transcribe: Upload an audio file for transcription
  • GET /health: Health check endpoint
  1. WebSocket API:
  • ws://localhost:8000/ws/transcribe: Real-time audio transcription

MCP Protocol

The server implements the Model Control Protocol (MCP) with the following message types:

  1. INIT: Initialize a new transcription session
  2. START: Begin audio streaming
  3. AUDIO: Send audio data
  4. TRANSCRIPTION: Receive transcription results
  5. ERROR: Error messages
  6. STOP: End audio streaming
  7. DONE: Complete session

Development

Running Tests

pytest tests/

Project Structure

elevenlabs-scribe-mcp-server/
├── elevenlabs_scribe_mcp_server/
│   ├── __init__.py
│   ├── main.py              # FastAPI server
│   └── mcp/
│       ├── __init__.py
│       ├── protocol.py      # MCP protocol handler
│       ├── types.py         # Protocol types
│       └── elevenlabs.py    # ElevenLabs implementation
├── examples/
│   └── client_example.py    # Example client
├── tests/
│   └── test_transcribe.py   # Test suite
├── pyproject.toml           # Project metadata
└── README.md

Requirements

  • Python 3.8+
  • FastAPI
  • Uvicorn
  • PyAudio (for microphone support)
  • aiohttp
  • python-dotenv
  • pydantic

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

MIT License - see LICENSE file for details.

Acknowledgments

  • ElevenLabs for their excellent Scribe API
  • FastAPI for the modern web framework
  • The Python community for the amazing tools and libraries

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Bora Yalcin
  • Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • apappascs
  • Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP servers, complete with features, documentation links, and contributors.

  • ShrimpingIt
  • Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx

  • OffchainLabs
  • Go implementation of Ethereum proof of stake

  • huahuayu
  • A unified API gateway for integrating multiple etherscan-like blockchain explorer APIs with Model Context Protocol (MCP) support for AI assistants.

  • modelcontextprotocol
  • Model Context Protocol Servers

  • Mintplex-Labs
  • The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

    Reviews

    1 (1)
    Avatar
    user_DNJ2BBDg
    2025-04-15

    Couchbase MCP Server for LLMs is a game-changer! This server offers unparalleled scalability and speed for managing large language models. Aniket310101 has truly outdone themselves with this release, making it easier than ever to deploy and maintain complex ML tasks. Highly recommend! Check it out [here](https://mcp.so/server/MCP-Server-Couchbase/Aniket310101).