ElevenLabs Scribe MCP Server logo

ElevenLabs Scribe MCP Server

by aromanstatue

An MCP server implementation for ElevenLabs' Scribe speech-to-text API, providing real-time transcription capabilities with advanced context management and bidirectional streaming. It supports both real-time and file-based transcription.

View on GitHub

Last updated: N/A

What is ElevenLabs Scribe MCP Server?

This is a Model Control Protocol (MCP) server that interfaces with ElevenLabs' Scribe API to provide real-time and file-based speech-to-text transcription services. It enables applications to stream audio and receive transcriptions with context management and bidirectional communication.

How to use ElevenLabs Scribe MCP Server?

  1. Clone the repository. 2. Create and activate a virtual environment. 3. Install dependencies using pip install -e .. 4. Create a .env file with your ElevenLabs API key. 5. Start the server using python -m elevenlabs_scribe_mcp_server.main. 6. Use the example client or integrate the MCP protocol into your application.

Key features of ElevenLabs Scribe MCP Server

  • Real-time Transcription

  • File-based Transcription

  • MCP Protocol Support

  • WebSocket Support

  • Context Management

  • Multiple Audio Formats

  • Language Detection

  • Event Detection

Use cases of ElevenLabs Scribe MCP Server

  • Real-time meeting transcription

  • Live captioning for streaming events

  • Voice assistant integration

  • Audio file analysis and transcription

FAQ from ElevenLabs Scribe MCP Server

What is the default port for the server?

The server starts on port 8000 by default, or the next available port if 8000 is in use.

How do I provide my ElevenLabs API key?

You need to create a .env file in the root directory of the project and set the ELEVENLABS_API_KEY variable to your API key.

What audio formats are supported?

The server supports various audio formats with automatic conversion.

How do I run the tests?

Run pytest tests/ in the project's root directory.

What are the requirements for running this server?

You need Python 3.8+, FastAPI, Uvicorn, PyAudio (for microphone support), aiohttp, python-dotenv, and pydantic.