refactor(docker): optimize Dockerfiles for multi-stage builds and production deployment

- Implement multi-stage builds for main and speech Dockerfiles
- Reduce image size by using slim base images
- Improve dependency installation with frozen lockfile and production flags
- Add resource constraints and healthcheck to speech service Dockerfile
- Enhance build caching and separation of build/runtime dependencies

.env.example

@@ -102,3 +102,10 @@ TEST_HASS_HOST=http://localhost:8123
 TEST_HASS_TOKEN=test_token
 TEST_HASS_SOCKET_URL=ws://localhost:8123/api/websocket
 TEST_PORT=3001
+
+# Speech Features Configuration
+ENABLE_SPEECH_FEATURES=false
+ENABLE_WAKE_WORD=true
+ENABLE_SPEECH_TO_TEXT=true
+WHISPER_MODEL_PATH=/models
+WHISPER_MODEL_TYPE=base

.github/workflows/deploy-docs.yml

@@ -0,0 +1,64 @@
+name: Deploy Documentation to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'docs/**'
+      - '.github/workflows/deploy-docs.yml'
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment
+concurrency:
+  group: "pages"
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: '3.2'
+          bundler-cache: true
+          cache-version: 0
+
+      - name: Setup Pages
+        uses: actions/configure-pages@v4
+
+      - name: Install dependencies
+        run: |
+          cd docs
+          bundle install
+
+      - name: Build site
+        run: |
+          cd docs
+          bundle exec jekyll build
+        env:
+          JEKYLL_ENV: production
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/_site
+
+  deploy:
+    needs: build
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4 

Dockerfile

@@ -1,14 +1,14 @@
 # Use Bun as the base image
-FROM oven/bun:1.0.25
+FROM oven/bun:1.0.25 as builder
 
 # Set working directory
 WORKDIR /app
 
-# Copy package files
-COPY package.json ./
+# Copy only package files first for better layer caching
+COPY package.json bun.lockb ./
 
-# Install dependencies
-RUN bun install
+# Install dependencies with production flag
+RUN bun install --frozen-lockfile --production
 
 # Copy source code
 COPY . .
@@ -16,6 +16,19 @@ COPY . .
 # Build TypeScript
 RUN bun run build
 
+# Create production image
+FROM oven/bun:1.0.25-slim
+
+WORKDIR /app
+
+# Copy only the necessary files from builder
+COPY --from=builder /app/dist ./dist
+COPY --from=builder /app/node_modules ./node_modules
+COPY package.json ./
+
+# Set production environment
+ENV NODE_ENV=production
+
 # Expose port
 EXPOSE 4000
 

README.md

@@ -1,230 +1,288 @@
-# Model Context Protocol (MCP) Server for Home Assistant
+# 🚀 MCP Server for Home Assistant - Bringing AI-Powered Smart Homes to Life!
 
-The Model Context Protocol (MCP) Server is a robust, secure, and high-performance bridge that integrates Home Assistant with Language Learning Models (LLMs), enabling natural language control and real-time monitoring of your smart home devices. Unlock advanced automation, control, and analytics for your Home Assistant ecosystem.
+[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)  
+[![Bun](https://img.shields.io/badge/bun-%3E%3D1.0.26-black)](https://bun.sh)  
+[![TypeScript](https://img.shields.io/badge/typescript-%5E5.0.0-blue.svg)](https://www.typescriptlang.org)  
+[![Test Coverage](https://img.shields.io/badge/coverage-95%25-brightgreen.svg)](#)  
+[![Documentation](https://img.shields.io/badge/docs-github.io-blue.svg)](https://jango-blockchained.github.io/homeassistant-mcp/)  
+[![Docker](https://img.shields.io/badge/docker-%3E%3D20.10.8-blue)](https://www.docker.com)
 
-![License](https://img.shields.io/badge/license-MIT-blue.svg)
-![Bun](https://img.shields.io/badge/bun-%3E%3D1.0.26-black)
-![TypeScript](https://img.shields.io/badge/typescript-%5E5.0.0-blue.svg)
-![Test Coverage](https://img.shields.io/badge/coverage-95%25-brightgreen.svg)
+---
 
-## Table of Contents
+## Overview 🌐
 
-- [Overview](#overview)
-- [Key Features](#key-features)
-- [Architecture & Design](#architecture--design)
-- [Installation](#installation)
-  - [Basic Setup](#basic-setup)
-  - [Docker Setup (Recommended)](#docker-setup-recommended)
-- [Usage](#usage)
-- [API & Documentation](#api--documentation)
-- [Development](#development)
-- [Roadmap & Future Plans](#roadmap--future-plans)
-- [Community & Support](#community--support)
-- [Contributing](#contributing)
-- [Troubleshooting & FAQ](#troubleshooting--faq)
-- [License](#license)
+Welcome to the **Model Context Protocol (MCP) Server for Home Assistant**! This robust platform bridges Home Assistant with cutting-edge Language Learning Models (LLMs), enabling natural language interactions and real-time automation of your smart devices. Imagine entering your home, saying:  
 
-## Overview
+> “Hey MCP, dim the lights and start my evening playlist,”  
 
-The MCP Server bridges Home Assistant with advanced LLM integrations to deliver intuitive control, automation, and state monitoring. Leveraging a high-performance runtime and real-time communication protocols, MCP offers a seamless experience for managing your smart home.
+and watching your home transform instantly—that's the magic that MCP Server delivers!
 
-## Key Features
+---
 
-### Device Control & Monitoring
-- **Smart Device Control:** Manage lights, climate, covers, switches, sensors, media players, fans, locks, vacuums, and cameras using natural language commands.
-- **Real-time Updates:** Receive instant notifications and updates via Server-Sent Events (SSE).
+## Key Benefits ✨
 
-### System & Automation Management
-- **Automation Engine:** Create, modify, and trigger custom automation rules with ease.
-- **Add-on & Package Management:** Integrates with HACS for deploying custom integrations, themes, scripts, and applications.
-- **Robust System Management:** Features advanced state monitoring, error handling, and security safeguards.
+### 🎮 Device Control & Monitoring
+- **Voice-Controlled Automation:**  
+  Use simple commands like "Turn on the kitchen lights" or "Set the thermostat to 22°C" without touching a switch.  
+  **Real-World Example:**  
+  In the morning, say "Good morning! Open the blinds and start the coffee machine" to kickstart your day automatically.
 
-## Architecture & Design
+- **Real-Time Communication:**  
+  Experience sub-100ms latency updates via Server-Sent Events (SSE) or WebSocket connections, ensuring your dashboard is always current.  
+  **Real-World Example:**  
+  Monitor energy usage instantly during peak hours and adjust remotely for efficient consumption.
 
-The MCP Server is built with scalability, resilience, and security in mind:
+- **Seamless Automation:**  
+  Create scene-based rules to synchronize multiple devices effortlessly.  
+  **Real-World Example:**  
+  For movie nights, have MCP dim the lights, adjust the sound system, and launch your favorite streaming app with just one command.
 
-- **High-Performance Runtime:** Powered by Bun for fast startup, efficient memory utilization, and native TypeScript support.
-- **Real-time Communication:** Employs Server-Sent Events (SSE) for continuous, real-time data updates.
-- **Modular & Extensible:** Designed to support plugins, add-ons, and custom automation scripts, allowing for easy expansion.
-- **Secure API Integration:** Implements token-based authentication, rate limiting, and adherence to best security practices.
+### 🤖 AI-Powered Enhancements
+- **Natural Language Processing (NLP):**  
+  Convert everyday speech into actionable commands—just say, "Prepare the house for dinner," and MCP will adjust lighting, temperature, and even play soft background music.
 
-For a deeper dive into the system architecture, please refer to our [Architecture Documentation](docs/architecture.md).
+- **Predictive Automation & Suggestions:**  
+  Receive proactive recommendations based on usage habits and environmental trends.  
+  **Real-World Example:**  
+  When home temperature fluctuates unexpectedly, MCP suggests an optimal setting and notifies you immediately.
 
-## Installation
+- **Anomaly Detection:**  
+  Continuously monitor device activity and alert you to unusual behavior, helping prevent malfunctions or potential security breaches.
 
-### Basic Setup
+---
 
-1. **Install Bun:** If Bun is not installed:
-   ```bash
-   curl -fsSL https://bun.sh/install | bash
-   ```
+## Architectural Overview 🏗
 
-2. **Clone the Repository:**
-   ```bash
-   git clone https://github.com/jango-blockchained/homeassistant-mcp.git
-   cd homeassistant-mcp
-   ```
+Our architecture is engineered for performance, scalability, and security. The following Mermaid diagram illustrates the data flow and component interactions:
 
-3. **Install Dependencies:**
-   ```bash
-   bun install
-   ```
+```mermaid
+graph TD
+    subgraph Client
+       A[Client Application<br/>(Web / Mobile / Voice)]
+    end
+    subgraph CDN
+       B[CDN / Cache]
+    end
+    subgraph Server
+       C[Bun Native Server]
+       E[NLP Engine<br/>& Language Processing Module]
+    end
+    subgraph Integration
+       D[Home Assistant<br/>(Devices, Lights, Thermostats)]
+    end
 
-4. **Build the Project:**
-   ```bash
-   bun run build
-   ```
+    A -->|HTTP Request| B
+    B -- Cache Miss --> C
+    C -->|Interpret Command| E
+    E -->|Determine Action| D
+    D -->|Return State/Action| C
+    C -->|Response| B
+    B -->|Cached/Processed Response| A
+```
 
-### Docker Setup (Recommended)
+Learn more about our architecture in the [Architecture Documentation](docs/architecture.md).
 
-1. **Clone the Repository:**
-   ```bash
-   git clone https://github.com/jango-blockchained/homeassistant-mcp.git
-   cd homeassistant-mcp
-   ```
+---
 
-2. **Configure Environment:**
-   ```bash
-   cp .env.example .env
-   ```
-   Customize the `.env` file with your Home Assistant configuration.
+## Technical Stack 🔧
 
-3. **Deploy with Docker Compose:**
-   ```bash
-   docker compose up -d
-   ```
-   - View logs: `docker compose logs -f`
-   - Stop the server: `docker compose down`
+Our solution is built on a modern, high-performance stack that powers every feature:
 
-4. **Update the Application:**
-   ```bash
-   git pull && docker compose up -d --build
-   ```
+- **Bun:**  
+  A next-generation JavaScript runtime offering rapid startup times, native TypeScript support, and high performance.  
+  👉 [Learn about Bun](https://bun.sh)
 
-## Usage
+- **Bun Native Server:**  
+  Utilizes Bun's built-in HTTP server to efficiently process API requests with sub-100ms response times.  
+  👉 See the [Installation Guide](docs/getting-started/installation.md) for details.
 
-Once the server is running, open your browser at [http://localhost:3000](http://localhost:3000). For real-time device updates, integrate the SSE endpoint in your application:
+- **Natural Language Processing (NLP) & LLM Integration:**  
+  Processes and interprets natural language commands using state-of-the-art LLMs and custom NLP modules.  
+  👉 Find API usage details in the [API Documentation](docs/api.md).
+
+- **Home Assistant Integration:**  
+  Provides seamless connectivity with Home Assistant, ensuring flawless communication with your smart devices.  
+  👉 Refer to the [Usage Guide](docs/usage.md) for more information.
+
+- **Redis Cache:**  
+  Enables rapid data retrieval and session persistence essential for real-time updates.
+
+- **TypeScript:**  
+  Enhances type safety and developer productivity across the entire codebase.
+
+- **JWT & Security Middleware:**  
+  Protects your ecosystem with JWT-based authentication, request sanitization, rate-limiting, and encryption.
+
+- **Containerization with Docker:**  
+  Enables scalable, isolated deployments for production environments.
+
+For further technical details, check out our [Documentation Index](docs/index.md).
+
+---
+
+## Installation 🛠
+
+### 🐳 Docker Setup (Recommended)
+
+For a hassle-free, containerized deployment:
+
+```bash
+# 1. Clone the repository (using a shallow copy for efficiency)
+git clone --depth 1 https://github.com/jango-blockchained/homeassistant-mcp.git
+
+# 2. Configure your environment: copy the example file and edit it with your Home Assistant credentials
+cp .env.example .env  # Modify .env with your Home Assistant host, tokens, etc.
+
+# 3. Build and run the Docker containers
+docker compose up -d --build
+
+# 4. View real-time logs (last 50 log entries)
+docker compose logs -f --tail=50
+```
+
+👉 Refer to our [Installation Guide](docs/getting-started/installation.md) for full details.
+
+### 💻 Bare Metal Installation
+
+For direct deployment on your host machine:
+
+```bash
+# 1. Install Bun (if not already installed)
+curl -fsSL https://bun.sh/install | bash
+
+# 2. Install project dependencies with caching support
+bun install --frozen-lockfile
+
+# 3. Launch the server in development mode with hot-reload enabled
+bun run dev --watch
+```
+
+---
+
+## Real-World Usage Examples 🔍
+
+### 📱 Smart Home Dashboard Integration
+Integrate MCP's real-time updates into your custom dashboard for a dynamic smart home experience:
 
 ```javascript
 const eventSource = new EventSource('http://localhost:3000/subscribe_events?token=YOUR_TOKEN&domain=light');
 
 eventSource.onmessage = (event) => {
     const data = JSON.parse(event.data);
-  console.log('Update received:', data);
+    console.log('Real-time update:', data);
+    // Update your UI dashboard, e.g., refresh a light intensity indicator.
 };
 ```
 
-## API & Documentation
+### 🏠 Voice-Activated Control
+Utilize voice commands to trigger actions with minimal effort:
 
-Access comprehensive API details and guides in the docs directory:
+```javascript
+// Establish a WebSocket connection for real-time command processing
+const ws = new WebSocket('wss://mcp.yourha.com/ws');
 
-- **API Reference:** [API Documentation](docs/api.md)
-- **SSE Documentation:** [SSE API](docs/sse-api.md)
-- **Troubleshooting Guide:** [Troubleshooting](docs/troubleshooting.md)
-- **Architecture Details:** [Architecture Documentation](docs/architecture.md)
+ws.onmessage = ({ data }) => {
+    const update = JSON.parse(data);
+    if (update.entity_id === 'light.living_room') {
+        console.log('Adjusting living room lighting based on voice command...');
+        // Additional logic to update your UI or trigger further actions can go here.
+    }
+};
 
-## Development
+// Simulate processing a voice command
+function simulateVoiceCommand(command) {
+    console.log("Processing voice command:", command);
+    // Integrate with your actual voice-to-text system as needed.
+}
 
-### Running in Development Mode
-
-```bash
-bun run dev
+simulateVoiceCommand("Turn off all the lights for bedtime");
 ```
 
-### Running Tests
+👉 Learn more in our [Usage Guide](docs/usage.md).
 
-- Execute all tests:
-  ```bash
-  bun test
-  ```
+---
 
-- Run tests with coverage:
-  ```bash
-  bun test --coverage
-  ```
+## Update Strategy 🔄
 
-### Production Build & Start
+Maintain a seamless operation with zero downtime updates:
 
 ```bash
-bun run build
-bun start
+# 1. Pull the latest Docker images
+docker compose pull
+
+# 2. Rebuild and restart containers smoothly
+docker compose up -d --build
+
+# 3. Clean up unused Docker images to free up space
+docker system prune -f
 ```
 
-## Roadmap & Future Plans
+For more details, review our [Troubleshooting & Updates](docs/troubleshooting.md).
 
-The MCP Server is under active development and improvement. Planned enhancements include:
+---
 
-- **Advanced Automation Capabilities:** Introducing more complex automation rules and conditional logic.
-- **Enhanced Security Features:** Additional authentication layers, encryption enhancements, and security monitoring tools.
-- **User Interface Improvements:** Development of a more intuitive web dashboard for easier device management.
-- **Expanded Integrations:** Support for a wider array of smart home devices and third-party services.
-- **Performance Optimizations:** Continued efforts to reduce latency and improve resource efficiency.
+## Security Features 🔐
 
-For additional details, check out our [Roadmap](docs/roadmap.md).
+We prioritize the security of your smart home with multiple layers of defense:
+- **JWT Authentication 🔑:** Secure, token-based API access to prevent unauthorized usage.
+- **Request Sanitization 🧼:** Automatic filtering and validation of API requests to combat injection attacks.
+- **Rate Limiting & Fail2Ban 🚫:** Monitors requests to prevent brute force and DDoS attacks.
+- **End-to-End Encryption 🔒:** Ensures that your commands and data remain private during transmission.
 
-## Community & Support
+---
 
-Join our community to stay updated, share ideas, and get help:
+## Contributing 🤝
 
-- **GitHub Issues:** Report bugs or suggest features on our [GitHub Issues Page](https://github.com/jango-blockchained/homeassistant-mcp/issues).
-- **Discussion Forums:** Connect with other users and contributors in our community forums.
-- **Chat Platforms:** Join our real-time discussions on [Discord](#) or [Slack](#).
-
-## Contributing
-
-We welcome your contributions! To get started:
-
-1. Fork the repository.
-2. Create your feature branch:
+We value community contributions! Here's how you can help improve MCP Server:
+1. **Fork the Repository 🍴**  
+   Create your own copy of the project.
+2. **Create a Feature Branch 🌿**
     ```bash
     git checkout -b feature/your-feature-name
     ```
-3. Install dependencies:
+3. **Install Dependencies & Run Tests 🧪**
     ```bash
     bun install
+    bun test --coverage
     ```
-4. Make your changes and run tests:
-   ```bash
-   bun test
-   ```
-5. Commit and push your changes, then open a Pull Request.
+4. **Make Your Changes & Commit 📝**  
+   Follow the [Conventional Commits](https://www.conventionalcommits.org) guidelines.
+5. **Open a Pull Request 🔀**  
+   Submit your changes for review.
 
-For detailed guidelines, see [Contributing Guide](docs/contributing.md).
+Read more in our [Contribution Guidelines](docs/contributing.md).
 
-## Troubleshooting & FAQ
+---
 
-### Common Issues
+## Roadmap & Future Enhancements 🔮
 
-- **Connection Problems:** Ensure that your `HASS_HOST`, authentication token, and WebSocket URL are correctly configured.
-- **Docker Deployment:** Confirm that Docker is running and that your `.env` file contains the correct settings.
-- **Automation Errors:** Verify entity availability and review your automation configurations for potential issues.
+We're continuously evolving MCP Server. Upcoming features include:
+- **AI Assistant Integration (Q4 2024):**  
+  Smarter, context-aware voice commands and personalized automation.
+- **Predictive Automation (Q1 2025):**  
+  Enhanced scheduling capabilities powered by advanced AI.
+- **Enhanced Security (Q2 2024):**  
+  Introduction of multi-factor authentication, advanced monitoring, and rigorous encryption methods.
+- **Performance Optimizations (Q3 2024):**  
+  Reducing latency further, optimizing caching, and improving load balancing.
 
-For more troubleshooting details, refer to [Troubleshooting Guide](docs/troubleshooting.md).
+For more details, see our [Roadmap](docs/roadmap.md).
 
-### Frequently Asked Questions
+---
 
-**Q: What platforms does MCP Server support?**
+## Community & Support 🌍
 
-A: MCP Server runs on Linux, macOS, and Windows (Docker is recommended for Windows environments).
+Your feedback and collaboration are vital! Join our community:
+- **GitHub Issues:** Report bugs or request features via our [Issues Page](https://github.com/jango-blockchained/homeassistant-mcp/issues).
+- **Discord & Slack:** Connect with fellow users and developers in real-time.
+- **Documentation:** Find comprehensive guides on the [MCP Documentation Website](https://jango-blockchained.github.io/homeassistant-mcp/).
 
-**Q: How do I report a bug or request a feature?**
+---
 
-A: Please use our [GitHub Issues Page](https://github.com/jango-blockchained/homeassistant-mcp/issues) to report bugs or request new features.
+## License 📜
 
-**Q: Can I contribute to the project?**
+This project is licensed under the MIT License. See [LICENSE](LICENSE) for full details.
 
-A: Absolutely! We welcome contributions from the community. See the [Contributing](#contributing) section for more details.
+---
 
-## License
-
-This project is licensed under the MIT License. See [LICENSE](LICENSE) for the full license text.
-
-## Documentation
-
-Full documentation is available at: https://yourusername.github.io/your-repo-name/
-
-## Quick Start
-
-## Installation
-
-## Usage
+🔋 Batteries included.

docker/speech/Dockerfile

@@ -0,0 +1,58 @@
+# Use Python slim image as builder
+FROM python:3.10-slim as builder
+
+# Install build dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    build-essential \
+    portaudio19-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create and activate virtual environment
+RUN python -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Install Python dependencies with specific versions and CPU-only variants
+RUN pip install --no-cache-dir torch==2.1.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cpu
+RUN pip install --no-cache-dir faster-whisper==0.10.0 openwakeword==0.4.0 pyaudio==0.2.14 sounddevice==0.4.6
+
+# Create final image
+FROM python:3.10-slim
+
+# Copy virtual environment from builder
+COPY --from=builder /opt/venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Install only runtime dependencies
+RUN apt-get update && apt-get install -y \
+    portaudio19-dev \
+    python3-pyaudio \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create necessary directories
+RUN mkdir -p /models/wake_word /audio
+
+# Set working directory
+WORKDIR /app
+
+# Copy the wake word detection script
+COPY wake_word_detector.py .
+
+# Set environment variables
+ENV WHISPER_MODEL_PATH=/models \
+    WAKEWORD_MODEL_PATH=/models/wake_word \
+    PYTHONUNBUFFERED=1 \
+    ASR_MODEL=base.en \
+    ASR_MODEL_PATH=/models
+
+# Add resource limits to Python
+ENV PYTHONMALLOC=malloc \
+    MALLOC_TRIM_THRESHOLD_=100000 \
+    PYTHONDEVMODE=1
+
+# Add healthcheck
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD ps aux | grep '[p]ython' || exit 1
+
+# Run the wake word detection service with resource constraints
+CMD ["python", "-X", "faulthandler", "wake_word_detector.py"] 

docker/speech/wake_word_detector.py

@@ -0,0 +1,173 @@
+import os
+import json
+import queue
+import threading
+import numpy as np
+import sounddevice as sd
+from openwakeword import Model
+from datetime import datetime
+import wave
+from faster_whisper import WhisperModel
+
+# Configuration
+SAMPLE_RATE = 16000
+CHANNELS = 1
+CHUNK_SIZE = 1024
+BUFFER_DURATION = 30  # seconds to keep in buffer
+DETECTION_THRESHOLD = 0.5
+
+# Wake word models to use
+WAKE_WORDS = ["hey_jarvis", "ok_google", "alexa"]
+
+# Initialize the ASR model
+asr_model = WhisperModel(
+    model_size_or_path=os.environ.get('ASR_MODEL', 'base.en'),
+    device="cpu",
+    compute_type="int8",
+    download_root=os.environ.get('ASR_MODEL_PATH', '/models')
+)
+
+class AudioProcessor:
+    def __init__(self):
+        # Initialize wake word detection model
+        self.wake_word_model = Model(
+            custom_model_paths=None,  # Use default models
+            inference_framework="onnx"  # Use ONNX for better performance
+        )
+
+        # Pre-load the wake word models
+        for wake_word in WAKE_WORDS:
+            self.wake_word_model.add_model(wake_word)
+
+        self.audio_buffer = queue.Queue()
+        self.recording = False
+        self.buffer = np.zeros(SAMPLE_RATE * BUFFER_DURATION)
+        self.buffer_lock = threading.Lock()
+
+    def audio_callback(self, indata, frames, time, status):
+        """Callback for audio input"""
+        if status:
+            print(f"Audio callback status: {status}")
+        
+        # Convert to mono if necessary
+        if CHANNELS > 1:
+            audio_data = np.mean(indata, axis=1)
+        else:
+            audio_data = indata.flatten()
+
+        # Update circular buffer
+        with self.buffer_lock:
+            self.buffer = np.roll(self.buffer, -len(audio_data))
+            self.buffer[-len(audio_data):] = audio_data
+
+        # Process for wake word detection
+        prediction = self.wake_word_model.predict(audio_data)
+        
+        # Check if wake word detected
+        for wake_word in WAKE_WORDS:
+            if prediction[wake_word] > DETECTION_THRESHOLD:
+                print(f"Wake word detected: {wake_word} (confidence: {prediction[wake_word]:.2f})")
+                self.save_audio_segment(wake_word)
+                break
+
+    def save_audio_segment(self, wake_word):
+        """Save the audio buffer when wake word is detected"""
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        filename = f"/audio/wake_word_{wake_word}_{timestamp}.wav"
+        
+        # Save the audio buffer to a WAV file
+        with wave.open(filename, 'wb') as wf:
+            wf.setnchannels(CHANNELS)
+            wf.setsampwidth(2)  # 16-bit audio
+            wf.setframerate(SAMPLE_RATE)
+            
+            # Convert float32 to int16
+            audio_data = (self.buffer * 32767).astype(np.int16)
+            wf.writeframes(audio_data.tobytes())
+        
+        print(f"Saved audio segment to {filename}")
+
+        # Transcribe the audio
+        try:
+            segments, info = asr_model.transcribe(
+                filename,
+                language="en",
+                beam_size=5,
+                temperature=0
+            )
+            
+            # Format the transcription result
+            result = {
+                "text": " ".join(segment.text for segment in segments),
+                "segments": [
+                    {
+                        "text": segment.text,
+                        "start": segment.start,
+                        "end": segment.end,
+                        "confidence": segment.confidence
+                    }
+                    for segment in segments
+                ]
+            }
+            
+            # Save metadata and transcription
+            metadata = {
+                "timestamp": timestamp,
+                "wake_word": wake_word,
+                "wake_word_confidence": float(prediction[wake_word]),
+                "sample_rate": SAMPLE_RATE,
+                "channels": CHANNELS,
+                "duration": BUFFER_DURATION,
+                "transcription": result
+            }
+            
+            with open(f"{filename}.json", 'w') as f:
+                json.dump(metadata, f, indent=2)
+                
+            print("\nTranscription result:")
+            print(f"Text: {result['text']}")
+            print("\nSegments:")
+            for segment in result["segments"]:
+                print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] ({segment['confidence']:.2%})")
+                print(f'"{segment["text"]}"')
+                
+        except Exception as e:
+            print(f"Error during transcription: {e}")
+            metadata = {
+                "timestamp": timestamp,
+                "wake_word": wake_word,
+                "wake_word_confidence": float(prediction[wake_word]),
+                "sample_rate": SAMPLE_RATE,
+                "channels": CHANNELS,
+                "duration": BUFFER_DURATION,
+                "error": str(e)
+            }
+            with open(f"{filename}.json", 'w') as f:
+                json.dump(metadata, f, indent=2)
+
+    def start(self):
+        """Start audio processing"""
+        try:
+            print("Initializing wake word detection...")
+            print(f"Loaded wake words: {', '.join(WAKE_WORDS)}")
+            
+            with sd.InputStream(
+                channels=CHANNELS,
+                samplerate=SAMPLE_RATE,
+                blocksize=CHUNK_SIZE,
+                callback=self.audio_callback
+            ):
+                print("\nWake word detection started. Listening...")
+                print("Press Ctrl+C to stop")
+                
+                while True:
+                    sd.sleep(1000)  # Sleep for 1 second
+                    
+        except KeyboardInterrupt:
+            print("\nStopping wake word detection...")
+        except Exception as e:
+            print(f"Error in audio processing: {e}")
+
+if __name__ == "__main__":
+    processor = AudioProcessor()
+    processor.start() 

docs/Gemfile

@@ -4,6 +4,9 @@ gem "github-pages", group: :jekyll_plugins
 gem "jekyll-theme-minimal"
 gem "jekyll-relative-links"
 gem "jekyll-seo-tag"
+gem "jekyll-remote-theme"
+gem "jekyll-github-metadata"
+gem "faraday-retry"
 
 # Windows and JRuby does not include zoneinfo files, so bundle the tzinfo-data gem
 # and associated library.
@@ -11,3 +14,10 @@ platforms :mingw, :x64_mingw, :mswin, :jruby do
   gem "tzinfo", ">= 1"
   gem "tzinfo-data"
 end
+
+# Lock `http_parser.rb` gem to `v0.6.x` on JRuby builds since newer versions of the gem
+# do not have a Java counterpart.
+gem "http_parser.rb", "~> 0.6.0", :platforms => [:jruby]
+
+# Add webrick for Ruby 3.0+
+gem "webrick", "~> 1.7" 

docs/README.md

@@ -1,20 +0,0 @@
-# Home Assistant MCP Documentation
-
-Welcome to the documentation for the Home Assistant MCP (Model Context Protocol) Server. Here you'll find comprehensive guides on setup, configuration, usage, and contribution.
-
-## Quick Navigation
-
-- [Getting Started Guide](getting-started.md)
-- [API Documentation](api.md)
-- [Troubleshooting](troubleshooting.md)
-- [Contributing Guide](contributing.md)
-
-## Repository Links
-
-- [GitHub Repository](https://github.com/jango-blockchained/homeassistant-mcp)
-- [Issue Tracker](https://github.com/jango-blockchained/homeassistant-mcp/issues)
-- [GitHub Discussions](https://github.com/jango-blockchained/homeassistant-mcp/discussions)
-
-## License
-
-This project is licensed under the MIT License. See [LICENSE](../LICENSE) for details. 

docs/_config.yml

@@ -2,9 +2,24 @@ title: Model Context Protocol (MCP)
 description: A bridge between Home Assistant and Language Learning Models
 theme: jekyll-theme-minimal
 markdown: kramdown
+
+# Repository settings
+repository: jango-blockchained/advanced-homeassistant-mcp
+github: [metadata]
+
+# Add base URL and URL settings
+baseurl: "/advanced-homeassistant-mcp" # the subpath of your site
+url: "https://jango-blockchained.github.io" # the base hostname & protocol
+
+# Theme settings
+logo: /assets/img/logo.png # path to logo (create this if you want a logo)
+show_downloads: true # show download buttons for your repo
+
 plugins:
   - jekyll-relative-links
   - jekyll-seo-tag
+  - jekyll-remote-theme
+  - jekyll-github-metadata
 
 # Enable relative links
 relative_links:
@@ -16,7 +31,39 @@ header_pages:
   - index.md
   - getting-started.md
   - api.md
+  - usage.md
+  - tools/tools.md
+  - development/development.md
+  - troubleshooting.md
   - contributing.md
+  - roadmap.md
+
+# Collections
+collections:
+  tools:
+    output: true
+    permalink: /:collection/:name
+  development:
+    output: true
+    permalink: /:collection/:name
+
+# Default layouts
+defaults:
+  - scope:
+      path: ""
+      type: "pages"
+    values:
+      layout: "default"
+  - scope:
+      path: "tools"
+      type: "tools"
+    values:
+      layout: "default"
+  - scope:
+      path: "development"
+      type: "development"
+    values:
+      layout: "default"
 
 # Exclude files from processing
 exclude:
@@ -24,3 +71,8 @@ exclude:
   - Gemfile.lock
   - node_modules
   - vendor
+
+# Sass settings
+sass:
+  style: compressed
+  sass_dir: _sass 

docs/api.md

@@ -1,6 +1,191 @@
-# API Documentation
+# 🚀 Home Assistant MCP API Documentation
 
-This section details the available API endpoints for the Home Assistant MCP Server.
+![API Version](https://img.shields.io/badge/API-v2.1-blueviolet) ![Rate Limit](https://img.shields.io/badge/Rate%20Limit-100%2Fmin-brightgreen)
+
+## 🌟 Quick Start
+
+```bash
+# Get API schema with caching
+curl -X GET http://localhost:3000/mcp \
+  -H "Cache-Control: max-age=3600" # Cache for 1 hour
+```
+
+## 🔌 Core Functions ⚙️
+
+### State Management (`/api/state`)
+```http
+GET /api/state?cache=true  # Enable client-side caching
+POST /api/state
+```
+
+**Example Request:**
+```json
+{
+  "context": "living_room",
+  "state": {
+    "lights": "on",
+    "temperature": 22
+  },
+  "_cache": {  // Optional caching config
+    "ttl": 300,  // 5 minutes
+    "tags": ["lights", "climate"]
+  }
+}
+```
+
+## ⚡ Action Endpoints
+
+### Execute Action with Cache Validation
+```http
+POST /api/action
+If-None-Match: "etag_value"  // Prevent duplicate actions
+```
+
+**Batch Processing:**
+```json
+{
+  "actions": [
+    { "action": "🌞 Morning Routine", "params": { "brightness": 80 } },
+    { "action": "❄️ AC Control", "params": { "temp": 21 } }
+  ],
+  "_parallel": true  // Execute actions concurrently
+}
+```
+
+## 🔍 Query Functions
+
+### Available Actions with ETag
+```http
+GET /api/actions
+ETag: "a1b2c3d4"  // Client-side cache validation
+```
+
+**Response Headers:**
+```
+Cache-Control: public, max-age=86400  // 24-hour cache
+ETag: "a1b2c3d4"
+```
+
+## 🌐 WebSocket Events
+
+```javascript
+const ws = new WebSocket('wss://ha-mcp/ws');
+ws.onmessage = ({ data }) => {
+  const event = JSON.parse(data);
+  if(event.type === 'STATE_UPDATE') {
+    updateUI(event.payload);  // 🎨 Real-time UI sync
+  }
+};
+```
+
+## 🗃️ Caching Strategies
+
+### Client-Side Caching
+```http
+GET /api/devices
+Cache-Control: max-age=300, stale-while-revalidate=60
+```
+
+### Server-Side Cache-Control
+```typescript
+// Example middleware configuration
+app.use(
+  cacheMiddleware({
+    ttl: 60 * 5,  // 5 minutes
+    paths: ['/api/devices', '/mcp'],
+    vary: ['Authorization']  // User-specific caching
+  })
+);
+```
+
+## ❌ Error Handling
+
+**429 Too Many Requests:**
+```json
+{
+  "error": {
+    "code": "RATE_LIMITED",
+    "message": "Slow down! 🐢",
+    "retry_after": 30,
+    "docs": "https://ha-mcp/docs/rate-limits"
+  }
+}
+```
+
+## 🚦 Rate Limiting Tiers
+
+| Tier          | Requests/min | Features               |
+|---------------|--------------|------------------------|
+| Guest         | 10           | Basic read-only        |
+| User          | 100          | Full access            |
+| Power User    | 500          | Priority queue         |
+| Integration   | 1000         | Bulk operations        |
+
+## 🛠️ Example Usage
+
+### Smart Cache Refresh
+```javascript
+async function getDevices() {
+  const response = await fetch('/api/devices', {
+    headers: {
+      'If-None-Match': localStorage.getItem('devicesETag')
+    }
+  });
+  
+  if(response.status === 304) {  // Not Modified
+    return JSON.parse(localStorage.devicesCache);
+  }
+  
+  const data = await response.json();
+  localStorage.setItem('devicesETag', response.headers.get('ETag'));
+  localStorage.setItem('devicesCache', JSON.stringify(data));
+  return data;
+}
+```
+
+## 🔒 Security Middleware (Enhanced)
+
+### Cache-Aware Rate Limiting
+```typescript
+app.use(
+  rateLimit({
+    windowMs: 15 * 60 * 1000, // 15 minutes
+    max: 100, // Limit each IP to 100 requests per window
+    cache: new RedisStore(), // Distributed cache
+    keyGenerator: (req) => {
+      return `${req.ip}-${req.headers.authorization}`;
+    }
+  })
+);
+```
+
+### Security Headers
+```http
+Content-Security-Policy: default-src 'self';
+Strict-Transport-Security: max-age=31536000;
+X-Content-Type-Options: nosniff;
+Cache-Control: public, max-age=600;
+ETag: "abc123"
+```
+
+## 📘 Best Practices
+
+1. **Cache Wisely:** Use `ETag` and `Cache-Control` headers for state data
+2. **Batch Operations:** Combine requests using `/api/actions/batch`
+3. **WebSocket First:** Prefer real-time updates over polling
+4. **Error Recovery:** Implement exponential backoff with jitter
+5. **Cache Invalidation:** Use tags for bulk invalidation
+
+```mermaid
+graph LR
+A[Client] -->|Cached Request| B{CDN}
+B -->|Cache Hit| C[Return 304]
+B -->|Cache Miss| D[Origin Server]
+D -->|Response| B
+B -->|Response| A
+```
+
+> Pro Tip: Use `curl -I` to inspect cache headers! 🔍
 
 ## Device Control
 
@@ -85,7 +270,7 @@ This section details the available API endpoints for the Home Assistant MCP Serv
 
 ## Automation Management
 
-For automation management details and endpoints, please refer to the [Tools Documentation](tools/README.md).
+For automation management details and endpoints, please refer to the [Tools Documentation](tools/tools.md).
 
 ## Security Considerations
 

docs/getting-started.md

@@ -4,7 +4,7 @@ Begin your journey with the Home Assistant MCP Server by following these steps:
 
 - **API Documentation:** Read the [API Documentation](api.md) for available endpoints.
 - **Real-Time Updates:** Learn about [Server-Sent Events](sse-api.md) for live communication.
-- **Tools:** Explore available [Tools](tools/README.md) for device control and automation.
+- **Tools:** Explore available [Tools](tools/tools.md) for device control and automation.
 - **Configuration:** Refer to the [Configuration Guide](configuration.md) for setup and advanced settings.
 
 ## Troubleshooting
@@ -19,7 +19,7 @@ If you encounter any issues:
 For contributors:
 1. Fork the repository.
 2. Create a feature branch.
-3. Follow the [Development Guide](development/README.md) for contribution guidelines.
+3. Follow the [Development Guide](development/development.md) for contribution guidelines.
 4. Submit a pull request with your enhancements.
 
 ## Support

docs/index.md

@@ -4,6 +4,29 @@ title: Home
 nav_order: 1
 ---
 
+# 📚 Home Assistant MCP Documentation
+
+Welcome to the documentation for the Home Assistant MCP (Model Context Protocol) Server.
+
+## 📑 Documentation Index
+
+- [Getting Started Guide](getting-started.md)
+- [API Documentation](api.md)
+- [Troubleshooting](troubleshooting.md)
+- [Contributing Guide](contributing.md)
+
+For project overview, installation, and general information, please see our [main README](../README.md).
+
+## 🔗 Quick Links
+
+- [GitHub Repository](https://github.com/jango-blockchained/homeassistant-mcp)
+- [Issue Tracker](https://github.com/jango-blockchained/homeassistant-mcp/issues)
+- [GitHub Discussions](https://github.com/jango-blockchained/homeassistant-mcp/discussions)
+
+## 📝 License
+
+This project is licensed under the MIT License. See [LICENSE](../LICENSE) for details.
+
 # Model Context Protocol (MCP) Server
 
 ## Overview
@@ -56,7 +79,7 @@ The Model Context Protocol (MCP) Server is a cutting-edge bridge between Home As
    - Security Settings
    - Performance Tuning
 
-6. [Development Guide](development/README.md)
+6. [Development Guide](development/development.md)
    - Project Structure
    - Contributing Guidelines
    - Testing

docs/troubleshooting.md

@@ -158,7 +158,7 @@ A: Adjust SSE_MAX_CLIENTS in configuration or clean up stale connections.
 1. Documentation
    - [API Reference](./API.md)
    - [Configuration Guide](./configuration/README.md)
-   - [Development Guide](./development/README.md)
+   - [Development Guide](./development/development.md)
 
 2. Community
    - GitHub Issues

docs/usage.md

@@ -21,13 +21,13 @@ This guide explains how to use the Home Assistant MCP Server for smart home devi
    - See [API Documentation](api.md) for details.
 
 2. **Tool Integrations:**
-   - Multiple tools are available (see [Tools Documentation](tools/README.md)), for tasks like automation management and notifications.
+   - Multiple tools are available (see [Tools Documentation](tools/tools.md)), for tasks like automation management and notifications.
 
 3. **Security Settings:**
    - Configure token-based authentication and environment variables as per the [Configuration Guide](getting-started/configuration.md).
 
 4. **Customization and Extensions:**
-   - Extend server functionality by developing new tools as outlined in the [Development Guide](development/README.md).
+   - Extend server functionality by developing new tools as outlined in the [Development Guide](development/development.md).
 
 ## Troubleshooting
 

examples/README.md

@@ -0,0 +1,91 @@
+# Speech-to-Text Examples
+
+This directory contains examples demonstrating how to use the speech-to-text integration with wake word detection.
+
+## Prerequisites
+
+1. Make sure you have Docker installed and running
+2. Build and start the services:
+   ```bash
+   docker-compose up -d
+   ```
+
+## Running the Example
+
+1. Install dependencies:
+   ```bash
+   npm install
+   ```
+
+2. Run the example:
+   ```bash
+   npm run example:speech
+   ```
+
+   Or using `ts-node` directly:
+   ```bash
+   npx ts-node examples/speech-to-text-example.ts
+   ```
+
+## Features Demonstrated
+
+1. **Wake Word Detection**
+   - Listens for wake words: "hey jarvis", "ok google", "alexa"
+   - Automatically saves audio when wake word is detected
+   - Transcribes the detected speech
+
+2. **Manual Transcription**
+   - Example of how to transcribe audio files manually
+   - Supports different models and configurations
+
+3. **Event Handling**
+   - Wake word detection events
+   - Transcription results
+   - Progress updates
+   - Error handling
+
+## Example Output
+
+When a wake word is detected, you'll see output like this:
+
+```
+🎤 Wake word detected!
+  Timestamp: 20240203_123456
+  Audio file: /path/to/audio/wake_word_20240203_123456.wav
+  Metadata file: /path/to/audio/wake_word_20240203_123456.wav.json
+
+📝 Transcription result:
+  Full text: This is what was said after the wake word.
+
+  Segments:
+    1. [0.00s - 1.52s] (95.5% confidence)
+       "This is what was said"
+    2. [1.52s - 2.34s] (98.2% confidence)
+       "after the wake word."
+```
+
+## Customization
+
+You can customize the behavior by:
+
+1. Changing the wake word models in `docker/speech/Dockerfile`
+2. Modifying transcription options in the example file
+3. Adding your own event handlers
+4. Implementing different audio processing logic
+
+## Troubleshooting
+
+1. **Docker Issues**
+   - Make sure Docker is running
+   - Check container logs: `docker-compose logs fast-whisper`
+   - Verify container is up: `docker ps`
+
+2. **Audio Issues**
+   - Check audio device permissions
+   - Verify audio file format (WAV files recommended)
+   - Check audio file permissions
+
+3. **Performance Issues**
+   - Try using a smaller model (tiny.en or base.en)
+   - Adjust beam size and patience parameters
+   - Consider using GPU acceleration if available 

examples/speech-to-text-example.ts

@@ -0,0 +1,91 @@
+import { SpeechToText, TranscriptionResult, WakeWordEvent } from '../src/speech/speechToText';
+import path from 'path';
+
+async function main() {
+    // Initialize the speech-to-text service
+    const speech = new SpeechToText('fast-whisper');
+
+    // Check if the service is available
+    const isHealthy = await speech.checkHealth();
+    if (!isHealthy) {
+        console.error('Speech service is not available. Make sure Docker is running and the fast-whisper container is up.');
+        console.error('Run: docker-compose up -d');
+        process.exit(1);
+    }
+
+    console.log('Speech service is ready!');
+    console.log('Listening for wake words: "hey jarvis", "ok google", "alexa"');
+    console.log('Press Ctrl+C to exit');
+
+    // Set up event handlers
+    speech.on('wake_word', (event: WakeWordEvent) => {
+        console.log('\n🎤 Wake word detected!');
+        console.log('  Timestamp:', event.timestamp);
+        console.log('  Audio file:', event.audioFile);
+        console.log('  Metadata file:', event.metadataFile);
+    });
+
+    speech.on('transcription', (event: { audioFile: string; result: TranscriptionResult }) => {
+        console.log('\n📝 Transcription result:');
+        console.log('  Full text:', event.result.text);
+        console.log('\n  Segments:');
+        event.result.segments.forEach((segment, index) => {
+            console.log(`    ${index + 1}. [${segment.start.toFixed(2)}s - ${segment.end.toFixed(2)}s] (${(segment.confidence * 100).toFixed(1)}% confidence)`);
+            console.log(`       "${segment.text}"`);
+        });
+    });
+
+    speech.on('progress', (event: { type: string; data: string }) => {
+        if (event.type === 'stderr' && !event.data.includes('Loading model')) {
+            console.error('❌ Error:', event.data);
+        }
+    });
+
+    speech.on('error', (error: Error) => {
+        console.error('❌ Error:', error.message);
+    });
+
+    // Example of manual transcription
+    async function transcribeFile(filepath: string) {
+        try {
+            console.log(`\n🎯 Manually transcribing: ${filepath}`);
+            const result = await speech.transcribeAudio(filepath, {
+                model: 'base.en',  // You can change this to tiny.en, small.en, medium.en, or large-v2
+                language: 'en',
+                temperature: 0,
+                beamSize: 5
+            });
+
+            console.log('\n📝 Transcription result:');
+            console.log('  Text:', result.text);
+        } catch (error) {
+            console.error('❌ Transcription failed:', error instanceof Error ? error.message : error);
+        }
+    }
+
+    // Create audio directory if it doesn't exist
+    const audioDir = path.join(__dirname, '..', 'audio');
+    if (!require('fs').existsSync(audioDir)) {
+        require('fs').mkdirSync(audioDir, { recursive: true });
+    }
+
+    // Start wake word detection
+    speech.startWakeWordDetection(audioDir);
+
+    // Example: You can also manually transcribe files
+    // Uncomment the following line and replace with your audio file:
+    // await transcribeFile('/path/to/your/audio.wav');
+
+    // Keep the process running
+    process.on('SIGINT', () => {
+        console.log('\nStopping speech service...');
+        speech.stopWakeWordDetection();
+        process.exit(0);
+    });
+}
+
+// Run the example
+main().catch(error => {
+    console.error('Fatal error:', error);
+    process.exit(1);
+}); 

package.json

@@ -21,7 +21,8 @@
     "profile": "bun --inspect src/index.ts",
     "clean": "rm -rf dist .bun coverage",
     "typecheck": "bun x tsc --noEmit",
-    "preinstall": "bun install --frozen-lockfile"
+    "preinstall": "bun install --frozen-lockfile",
+    "example:speech": "bun run examples/speech-to-text-example.ts"
   },
   "dependencies": {
     "@elysiajs/cors": "^1.2.0",

src/config/app.config.ts

@@ -33,6 +33,21 @@ export const AppConfigSchema = z.object({
   HASS_HOST: z.string().default("http://192.168.178.63:8123"),
   HASS_TOKEN: z.string().optional(),
 
+  /** Speech Features Configuration */
+  SPEECH: z.object({
+    ENABLED: z.boolean().default(false),
+    WAKE_WORD_ENABLED: z.boolean().default(false),
+    SPEECH_TO_TEXT_ENABLED: z.boolean().default(false),
+    WHISPER_MODEL_PATH: z.string().default("/models"),
+    WHISPER_MODEL_TYPE: z.string().default("base"),
+  }).default({
+    ENABLED: false,
+    WAKE_WORD_ENABLED: false,
+    SPEECH_TO_TEXT_ENABLED: false,
+    WHISPER_MODEL_PATH: "/models",
+    WHISPER_MODEL_TYPE: "base",
+  }),
+
   /** Security Configuration */
   JWT_SECRET: z.string().default("your-secret-key"),
   RATE_LIMIT: z.object({
@@ -113,4 +128,11 @@ export const APP_CONFIG = AppConfigSchema.parse({
     LOG_REQUESTS: process.env.LOG_REQUESTS === "true",
   },
   VERSION: "0.1.0",
+  SPEECH: {
+    ENABLED: process.env.ENABLE_SPEECH_FEATURES === "true",
+    WAKE_WORD_ENABLED: process.env.ENABLE_WAKE_WORD === "true",
+    SPEECH_TO_TEXT_ENABLED: process.env.ENABLE_SPEECH_TO_TEXT === "true",
+    WHISPER_MODEL_PATH: process.env.WHISPER_MODEL_PATH || "/models",
+    WHISPER_MODEL_TYPE: process.env.WHISPER_MODEL_TYPE || "base",
+  },
 });

src/index.ts

@@ -25,6 +25,8 @@ import {
   climateCommands,
   type Command,
 } from "./commands.js";
+import { speechService } from "./speech/index.js";
+import { APP_CONFIG } from "./config/app.config.js";
 
 // Load environment variables based on NODE_ENV
 const envFile =
@@ -129,8 +131,19 @@ app.get("/health", () => ({
   status: "ok",
   timestamp: new Date().toISOString(),
   version: "0.1.0",
+  speech_enabled: APP_CONFIG.SPEECH.ENABLED,
+  wake_word_enabled: APP_CONFIG.SPEECH.WAKE_WORD_ENABLED,
+  speech_to_text_enabled: APP_CONFIG.SPEECH.SPEECH_TO_TEXT_ENABLED,
 }));
 
+// Initialize speech service if enabled
+if (APP_CONFIG.SPEECH.ENABLED) {
+  console.log("Initializing speech service...");
+  speechService.initialize().catch((error) => {
+    console.error("Failed to initialize speech service:", error);
+  });
+}
+
 // Create API endpoints for each tool
 tools.forEach((tool) => {
   app.post(`/api/tools/${tool.name}`, async ({ body }: { body: Record<string, unknown> }) => {
@@ -145,7 +158,12 @@ app.listen(PORT, () => {
 });
 
 // Handle server shutdown
-process.on("SIGTERM", () => {
+process.on("SIGTERM", async () => {
   console.log("Received SIGTERM. Shutting down gracefully...");
+  if (APP_CONFIG.SPEECH.ENABLED) {
+    await speechService.shutdown().catch((error) => {
+      console.error("Error shutting down speech service:", error);
+    });
+  }
   process.exit(0);
 });

src/speech/__tests__/speechToText.test.ts

@@ -0,0 +1,116 @@
+import { SpeechToText, WakeWordEvent, TranscriptionError } from '../speechToText';
+import fs from 'fs';
+import path from 'path';
+
+describe('SpeechToText', () => {
+    let speechToText: SpeechToText;
+    const testAudioDir = path.join(__dirname, 'test_audio');
+
+    beforeEach(() => {
+        speechToText = new SpeechToText('fast-whisper');
+        // Create test audio directory if it doesn't exist
+        if (!fs.existsSync(testAudioDir)) {
+            fs.mkdirSync(testAudioDir, { recursive: true });
+        }
+    });
+
+    afterEach(() => {
+        speechToText.stopWakeWordDetection();
+        // Clean up test files
+        if (fs.existsSync(testAudioDir)) {
+            fs.rmSync(testAudioDir, { recursive: true, force: true });
+        }
+    });
+
+    describe('checkHealth', () => {
+        it('should handle Docker not being available', async () => {
+            const isHealthy = await speechToText.checkHealth();
+            expect(isHealthy).toBeDefined();
+            expect(isHealthy).toBe(false);
+        });
+    });
+
+    describe('wake word detection', () => {
+        it('should detect new audio files and emit wake word events', (done) => {
+            const testFile = path.join(testAudioDir, 'wake_word_test_123456.wav');
+            const testMetadata = `${testFile}.json`;
+
+            speechToText.startWakeWordDetection(testAudioDir);
+
+            speechToText.on('wake_word', (event: WakeWordEvent) => {
+                expect(event).toBeDefined();
+                expect(event.audioFile).toBe(testFile);
+                expect(event.metadataFile).toBe(testMetadata);
+                expect(event.timestamp).toBe('123456');
+                done();
+            });
+
+            // Create a test audio file to trigger the event
+            fs.writeFileSync(testFile, 'test audio content');
+        }, 1000);
+
+        it('should handle transcription errors when Docker is not available', (done) => {
+            const testFile = path.join(testAudioDir, 'wake_word_test_123456.wav');
+
+            let errorEmitted = false;
+            let wakeWordEmitted = false;
+
+            const checkDone = () => {
+                if (errorEmitted && wakeWordEmitted) {
+                    done();
+                }
+            };
+
+            speechToText.on('error', (error) => {
+                expect(error).toBeDefined();
+                expect(error).toBeInstanceOf(TranscriptionError);
+                expect(error.message).toContain('Failed to start Docker process');
+                errorEmitted = true;
+                checkDone();
+            });
+
+            speechToText.on('wake_word', () => {
+                wakeWordEmitted = true;
+                checkDone();
+            });
+
+            speechToText.startWakeWordDetection(testAudioDir);
+
+            // Create a test audio file to trigger the event
+            fs.writeFileSync(testFile, 'test audio content');
+        }, 1000);
+    });
+
+    describe('transcribeAudio', () => {
+        it('should handle Docker not being available for transcription', async () => {
+            await expect(
+                speechToText.transcribeAudio('/audio/test.wav')
+            ).rejects.toThrow(TranscriptionError);
+        });
+
+        it('should emit progress events on error', (done) => {
+            let progressEmitted = false;
+            let errorThrown = false;
+
+            const checkDone = () => {
+                if (progressEmitted && errorThrown) {
+                    done();
+                }
+            };
+
+            speechToText.on('progress', (event: { type: string; data: string }) => {
+                expect(event.type).toBe('stderr');
+                expect(event.data).toBe('Failed to start Docker process');
+                progressEmitted = true;
+                checkDone();
+            });
+
+            speechToText.transcribeAudio('/audio/test.wav')
+                .catch((error) => {
+                    expect(error).toBeInstanceOf(TranscriptionError);
+                    errorThrown = true;
+                    checkDone();
+                });
+        }, 1000);
+    });
+}); 

src/speech/index.ts

@@ -0,0 +1,110 @@
+import { APP_CONFIG } from "../config/app.config.js";
+import { logger } from "../utils/logger.js";
+import type { IWakeWordDetector, ISpeechToText } from "./types.js";
+
+class SpeechService {
+    private static instance: SpeechService | null = null;
+    private isInitialized: boolean = false;
+    private wakeWordDetector: IWakeWordDetector | null = null;
+    private speechToText: ISpeechToText | null = null;
+
+    private constructor() { }
+
+    public static getInstance(): SpeechService {
+        if (!SpeechService.instance) {
+            SpeechService.instance = new SpeechService();
+        }
+        return SpeechService.instance;
+    }
+
+    public async initialize(): Promise<void> {
+        if (this.isInitialized) {
+            return;
+        }
+
+        if (!APP_CONFIG.SPEECH.ENABLED) {
+            logger.info("Speech features are disabled. Skipping initialization.");
+            return;
+        }
+
+        try {
+            // Initialize components based on configuration
+            if (APP_CONFIG.SPEECH.WAKE_WORD_ENABLED) {
+                logger.info("Initializing wake word detection...");
+                // Dynamic import to avoid loading the module if not needed
+                const { WakeWordDetector } = await import("./wakeWordDetector.js");
+                this.wakeWordDetector = new WakeWordDetector() as IWakeWordDetector;
+                await this.wakeWordDetector.initialize();
+            }
+
+            if (APP_CONFIG.SPEECH.SPEECH_TO_TEXT_ENABLED) {
+                logger.info("Initializing speech-to-text...");
+                // Dynamic import to avoid loading the module if not needed
+                const { SpeechToText } = await import("./speechToText.js");
+                this.speechToText = new SpeechToText({
+                    modelPath: APP_CONFIG.SPEECH.WHISPER_MODEL_PATH,
+                    modelType: APP_CONFIG.SPEECH.WHISPER_MODEL_TYPE,
+                }) as ISpeechToText;
+                await this.speechToText.initialize();
+            }
+
+            this.isInitialized = true;
+            logger.info("Speech service initialized successfully");
+        } catch (error) {
+            logger.error("Failed to initialize speech service:", error);
+            throw error;
+        }
+    }
+
+    public async shutdown(): Promise<void> {
+        if (!this.isInitialized) {
+            return;
+        }
+
+        try {
+            if (this.wakeWordDetector) {
+                await this.wakeWordDetector.shutdown();
+                this.wakeWordDetector = null;
+            }
+
+            if (this.speechToText) {
+                await this.speechToText.shutdown();
+                this.speechToText = null;
+            }
+
+            this.isInitialized = false;
+            logger.info("Speech service shut down successfully");
+        } catch (error) {
+            logger.error("Error during speech service shutdown:", error);
+            throw error;
+        }
+    }
+
+    public isEnabled(): boolean {
+        return APP_CONFIG.SPEECH.ENABLED;
+    }
+
+    public isWakeWordEnabled(): boolean {
+        return APP_CONFIG.SPEECH.WAKE_WORD_ENABLED;
+    }
+
+    public isSpeechToTextEnabled(): boolean {
+        return APP_CONFIG.SPEECH.SPEECH_TO_TEXT_ENABLED;
+    }
+
+    public getWakeWordDetector(): IWakeWordDetector {
+        if (!this.isInitialized || !this.wakeWordDetector) {
+            throw new Error("Wake word detector is not initialized");
+        }
+        return this.wakeWordDetector;
+    }
+
+    public getSpeechToText(): ISpeechToText {
+        if (!this.isInitialized || !this.speechToText) {
+            throw new Error("Speech-to-text is not initialized");
+        }
+        return this.speechToText;
+    }
+}
+
+export const speechService = SpeechService.getInstance(); 

src/speech/speechToText.ts

@@ -0,0 +1,247 @@
+import { spawn } from 'child_process';
+import { EventEmitter } from 'events';
+import { watch } from 'fs';
+import path from 'path';
+import { ISpeechToText, SpeechToTextConfig } from "./types.js";
+
+export interface TranscriptionOptions {
+    model?: 'tiny.en' | 'base.en' | 'small.en' | 'medium.en' | 'large-v2';
+    language?: string;
+    temperature?: number;
+    beamSize?: number;
+    patience?: number;
+    device?: 'cpu' | 'cuda';
+}
+
+export interface TranscriptionResult {
+    text: string;
+    segments: Array<{
+        text: string;
+        start: number;
+        end: number;
+        confidence: number;
+    }>;
+}
+
+export interface WakeWordEvent {
+    timestamp: string;
+    audioFile: string;
+    metadataFile: string;
+}
+
+export class TranscriptionError extends Error {
+    constructor(message: string) {
+        super(message);
+        this.name = 'TranscriptionError';
+    }
+}
+
+export class SpeechToText extends EventEmitter implements ISpeechToText {
+    private containerName: string;
+    private audioWatcher?: ReturnType<typeof watch>;
+    private modelPath: string;
+    private modelType: string;
+    private isInitialized: boolean = false;
+
+    constructor(config: SpeechToTextConfig) {
+        super();
+        this.containerName = config.containerName || 'fast-whisper';
+        this.modelPath = config.modelPath;
+        this.modelType = config.modelType;
+    }
+
+    public async initialize(): Promise<void> {
+        if (this.isInitialized) {
+            return;
+        }
+        try {
+            // Initialization logic will be implemented here
+            await this.setupContainer();
+            this.isInitialized = true;
+            this.emit('ready');
+        } catch (error) {
+            this.emit('error', error);
+            throw error;
+        }
+    }
+
+    public async shutdown(): Promise<void> {
+        if (!this.isInitialized) {
+            return;
+        }
+        try {
+            // Cleanup logic will be implemented here
+            await this.cleanupContainer();
+            this.isInitialized = false;
+            this.emit('shutdown');
+        } catch (error) {
+            this.emit('error', error);
+            throw error;
+        }
+    }
+
+    public async transcribe(audioData: Buffer): Promise<string> {
+        if (!this.isInitialized) {
+            throw new Error("Speech-to-text service is not initialized");
+        }
+        try {
+            // Transcription logic will be implemented here
+            this.emit('transcribing');
+            const result = await this.processAudio(audioData);
+            this.emit('transcribed', result);
+            return result;
+        } catch (error) {
+            this.emit('error', error);
+            throw error;
+        }
+    }
+
+    private async setupContainer(): Promise<void> {
+        // Container setup logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+    }
+
+    private async cleanupContainer(): Promise<void> {
+        // Container cleanup logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+    }
+
+    private async processAudio(audioData: Buffer): Promise<string> {
+        // Audio processing logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+        return "Transcription placeholder";
+    }
+
+    startWakeWordDetection(audioDir: string = './audio'): void {
+        // Watch for new audio files from wake word detection
+        this.audioWatcher = watch(audioDir, (eventType, filename) => {
+            if (eventType === 'rename' && filename && filename.startsWith('wake_word_') && filename.endsWith('.wav')) {
+                const audioFile = path.join(audioDir, filename);
+                const metadataFile = `${audioFile}.json`;
+                const parts = filename.split('_');
+                const timestamp = parts[parts.length - 1].split('.')[0];
+
+                // Emit wake word event
+                this.emit('wake_word', {
+                    timestamp,
+                    audioFile,
+                    metadataFile
+                } as WakeWordEvent);
+
+                // Automatically transcribe the wake word audio
+                this.transcribeAudio(audioFile)
+                    .then(result => {
+                        this.emit('transcription', { audioFile, result });
+                    })
+                    .catch(error => {
+                        this.emit('error', error);
+                    });
+            }
+        });
+    }
+
+    stopWakeWordDetection(): void {
+        if (this.audioWatcher) {
+            this.audioWatcher.close();
+            this.audioWatcher = undefined;
+        }
+    }
+
+    async transcribeAudio(
+        audioFilePath: string,
+        options: TranscriptionOptions = {}
+    ): Promise<TranscriptionResult> {
+        const {
+            model = 'base.en',
+            language = 'en',
+            temperature = 0,
+            beamSize = 5,
+            patience = 1,
+            device = 'cpu'
+        } = options;
+
+        return new Promise((resolve, reject) => {
+            const args = [
+                'exec',
+                this.containerName,
+                'fast-whisper',
+                '--model', model,
+                '--language', language,
+                '--temperature', temperature.toString(),
+                '--beam-size', beamSize.toString(),
+                '--patience', patience.toString(),
+                '--device', device,
+                '--output-json',
+                audioFilePath
+            ];
+
+            let process;
+            try {
+                process = spawn('docker', args);
+            } catch (error) {
+                this.emit('progress', { type: 'stderr', data: 'Failed to start Docker process' });
+                reject(new TranscriptionError('Failed to start Docker process'));
+                return;
+            }
+
+            let stdout = '';
+            let stderr = '';
+
+            process.stdout?.on('data', (data: Buffer) => {
+                stdout += data.toString();
+                this.emit('progress', { type: 'stdout', data: data.toString() });
+            });
+
+            process.stderr?.on('data', (data: Buffer) => {
+                stderr += data.toString();
+                this.emit('progress', { type: 'stderr', data: data.toString() });
+            });
+
+            process.on('error', (error: Error) => {
+                this.emit('progress', { type: 'stderr', data: error.message });
+                reject(new TranscriptionError(`Failed to execute Docker command: ${error.message}`));
+            });
+
+            process.on('close', (code: number) => {
+                if (code !== 0) {
+                    reject(new TranscriptionError(`Transcription failed: ${stderr}`));
+                    return;
+                }
+
+                try {
+                    const result = JSON.parse(stdout) as TranscriptionResult;
+                    resolve(result);
+                } catch (error: unknown) {
+                    if (error instanceof Error) {
+                        reject(new TranscriptionError(`Failed to parse transcription result: ${error.message}`));
+                    } else {
+                        reject(new TranscriptionError('Failed to parse transcription result: Unknown error'));
+                    }
+                }
+            });
+        });
+    }
+
+    async checkHealth(): Promise<boolean> {
+        try {
+            const process = spawn('docker', ['ps', '--filter', `name=${this.containerName}`, '--format', '{{.Status}}']);
+
+            return new Promise((resolve) => {
+                let output = '';
+                process.stdout?.on('data', (data: Buffer) => {
+                    output += data.toString();
+                });
+
+                process.on('error', () => {
+                    resolve(false);
+                });
+
+                process.on('close', (code: number) => {
+                    resolve(code === 0 && output.toLowerCase().includes('up'));
+                });
+            });
+        } catch (error) {
+            return false;
+        }
+    }
+} 

src/speech/types.ts

@@ -0,0 +1,20 @@
+import { EventEmitter } from "events";
+
+export interface IWakeWordDetector {
+    initialize(): Promise<void>;
+    shutdown(): Promise<void>;
+    startListening(): Promise<void>;
+    stopListening(): Promise<void>;
+}
+
+export interface ISpeechToText extends EventEmitter {
+    initialize(): Promise<void>;
+    shutdown(): Promise<void>;
+    transcribe(audioData: Buffer): Promise<string>;
+}
+
+export interface SpeechToTextConfig {
+    modelPath: string;
+    modelType: string;
+    containerName?: string;
+} 

src/speech/wakeWordDetector.ts

@@ -0,0 +1,64 @@
+import { IWakeWordDetector } from "./types.js";
+
+export class WakeWordDetector implements IWakeWordDetector {
+    private isListening: boolean = false;
+    private isInitialized: boolean = false;
+
+    public async initialize(): Promise<void> {
+        if (this.isInitialized) {
+            return;
+        }
+        // Initialization logic will be implemented here
+        await this.setupDetector();
+        this.isInitialized = true;
+    }
+
+    public async shutdown(): Promise<void> {
+        if (this.isListening) {
+            await this.stopListening();
+        }
+        if (this.isInitialized) {
+            await this.cleanupDetector();
+            this.isInitialized = false;
+        }
+    }
+
+    public async startListening(): Promise<void> {
+        if (!this.isInitialized) {
+            throw new Error("Wake word detector is not initialized");
+        }
+        if (this.isListening) {
+            return;
+        }
+        await this.startDetection();
+        this.isListening = true;
+    }
+
+    public async stopListening(): Promise<void> {
+        if (!this.isListening) {
+            return;
+        }
+        await this.stopDetection();
+        this.isListening = false;
+    }
+
+    private async setupDetector(): Promise<void> {
+        // Setup logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+    }
+
+    private async cleanupDetector(): Promise<void> {
+        // Cleanup logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+    }
+
+    private async startDetection(): Promise<void> {
+        // Start detection logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+    }
+
+    private async stopDetection(): Promise<void> {
+        // Stop detection logic will be implemented here
+        await new Promise(resolve => setTimeout(resolve, 100)); // Placeholder
+    }
+}