Enhance ElevenLabs README with comprehensive usage guide

Added a detailed "How to Use This Cookbook" section that guides users through:
- Step 1: Environment setup with API keys and dependencies
- Step 2: Working through the notebook to learn concepts
- Step 3: Running the production script for hands-on experience

Also expanded the "More About ElevenLabs" section with additional resources including Voice Library, API Playground, and SDK links.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

Author: Adriaan-ANT

third_party/ElevenLabs/README.md

@@ -2,14 +2,75 @@
 
 [ElevenLabs](https://elevenlabs.io/) provides AI-powered speech-to-text and text-to-speech APIs for creating natural-sounding voice applications with advanced features like voice cloning and streaming synthesis.
 
-* The [Low Latency Voice Assistant Notebook](./low_latency_stt_claude_tts.ipynb) demonstrates building a real-time voice assistant using ElevenLabs for speech processing and Claude for intelligent responses, with progressive optimizations to reduce latency through streaming.
+This cookbook demonstrates how to build a low-latency voice assistant by combining ElevenLabs' speech processing with Claude's intelligent responses, progressively optimizing for real-time performance.
 
-* The companion [WebSocket Streaming Script](./stream_voice_assistant_websocket.py) provides a production-ready implementation of a conversational voice assistant with continuous microphone input, gapless audio playback, and low latency.
+## What's Included
 
-# More about ElevenLabs
+* **[Low Latency Voice Assistant Notebook](./low_latency_stt_claude_tts.ipynb)** - An interactive tutorial that walks you through building a voice assistant step-by-step, demonstrating various optimization techniques to minimize latency through streaming.
 
-Learn more at [elevenlabs.io](https://elevenlabs.io) and view the [API Documentation](https://elevenlabs.io/docs/overview).
+* **[WebSocket Streaming Script](./stream_voice_assistant_websocket.py)** - A production-ready conversational voice assistant featuring continuous microphone input, gapless audio playback, and the lowest possible latency using WebSocket streaming.
 
-# Get Started
+## How to Use This Cookbook
 
-If you're ready to get started using ElevenLabs, head over to the [ElevenLabs Platform](https://elevenlabs.io/sign-up) to create a free account and get your API key with free monthly credits.
+We recommend following this sequence to get the most out of this cookbook:
+
+### Step 1: Set Up Your Environment
+
+1. **Get your API keys:**
+   - ElevenLabs API key: [elevenlabs.io/app/developers/api-keys](https://elevenlabs.io/app/developers/api-keys)
+   - Anthropic API key: [console.anthropic.com/settings/keys](https://console.anthropic.com/settings/keys)
+
+2. **Configure your environment:**
+   ```bash
+   cp .env.example .env
+   # Edit .env and add your API keys
+   ```
+
+3. **Install dependencies:**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+### Step 2: Work Through the Notebook
+
+Start with the **[Low Latency Voice Assistant Notebook](./low_latency_stt_claude_tts.ipynb)**. This interactive guide will teach you:
+
+- How to use ElevenLabs for speech-to-text transcription
+- How to generate Claude responses and measure latency
+- How streaming reduces time-to-first-token
+- How to stream text-to-speech for faster audio playback
+- The tradeoffs between different streaming approaches
+- Why WebSocket streaming provides the best balance of latency and quality
+
+The notebook includes performance metrics and comparisons at each step, helping you understand the impact of each optimization.
+
+### Step 3: Try the Production Script
+
+After understanding the concepts from the notebook, run the **[WebSocket Streaming Script](./stream_voice_assistant_websocket.py)** to experience a fully functional voice assistant:
+
+```bash
+python stream_voice_assistant_websocket.py
+```
+
+**How it works:**
+1. Press Enter to start recording
+2. Speak your question into the microphone
+3. Press Enter to stop recording
+4. The assistant will respond with natural speech
+5. Repeat or press Ctrl+C to exit
+
+The script demonstrates production-ready implementations of:
+- Real-time microphone recording with sounddevice
+- Continuous conversation with context retention
+- WebSocket-based streaming for minimal latency
+- Custom audio queue for seamless playback
+
+## More About ElevenLabs
+
+Here are some helpful resources to deepen your understanding:
+
+- [ElevenLabs Platform](https://elevenlabs.io/) - Official website
+- [API Documentation](https://elevenlabs.io/docs/overview) - Complete API reference
+- [Voice Library](https://elevenlabs.io/voice-library) - Explore available voices
+- [API Playground](https://elevenlabs.io/app/speech-synthesis/text-to-speech) - Test voices interactively
+- [Python SDK](https://github.com/elevenlabs/elevenlabs-python) - Official Python SDK