MCP_server

MCP_server

1
ai_chatbot

The Speech Analysis MCP Server is designed to analyze spoken English automatically using the MCP architecture. It features speech-to-text, grammar analysis, vocabulary and logic suggestions, and sentence comparison.

Speech Analysis MCP Server

This project is a speech analysis server using the Model Context Protocol (MCP) architecture for automatic analysis of spoken English content. It supports features such as speech-to-text, grammar error analysis, vocabulary suggestions, logical suggestions, and sentence comparison.

Features

  • Speech-to-Text: Processes audio files using the OpenAI Whisper model.
  • Grammar Check: Analyzes grammar errors.
  • Vocabulary Suggestions: Provides better word choices.
  • Logical Suggestions: Offers feedback on sentence structure and logic.
  • Sentence Comparison: Identifies discrepancies with the original text.

Installation Steps

  1. Clone the project repository and navigate into the directory.
  2. Create a virtual environment and install dependencies using pip.
  3. Start the MCP server using uvicorn main:app --reload.

API & Testing

Use main.py to post requests for tool analysis. See MCPtest.json for examples.

Supported Audio Formats

  • .mp3, .wav
  • Test audio files can be placed in the user_audio/ directory.