Add LiveKit patient intake voice agent example

[tinalenguyen]

A family-medicine front-desk voice agent running the full xAI speech stack — xai/stt-1, grok-4.20, and xai/tts-1 — with LiveKit Agents for transport and turn detection.

voice-examples/patient-intake/
agent/ Python agent: one agent, one conversation, eight typed tools over an
in-memory clinic. No handoffs or workflow state machine; every tool
re-verifies identity from its arguments. Dependencies are declared in
requirements.txt with ranges, matching the other Python examples here.
web/ Next.js app that dispatches the worker and renders the conversation,
transcript, and tool calls. The UI is assembled from the packaged
@livekit/components-react primitives (VoiceAssistantControlBar,
BarVisualizer) rather than hand-rolled, and ships no font binaries.

Per CONTRIBUTING.md: dependencies are declared and minimal, no credentials are committed (the gitleaks hook passes), and both halves run end to end from the documented steps. No registry.yaml entry is added — the registry covers the notebooks under examples/, and no voice example is listed there.

Description

Summary:

• "A summary of your changes"

Why this change matters:

• "Briefly explain its value or problem it solves"

Type(s) of Change

• New Content
• Content Improvement (e.g., enhancing existing content)
• Bug Fix
• Other

Checklist

• Read "How to Contribute" in CONTRIBUTING.md
• Code follows style guidelines in "How to Contribute"
• Included relevant dependencies
• API key is not in committed files
• Notebook runs end-to-end with cell outputs shown and no errors
• Added new notebook entry to registry.yaml (if PR adds a new notebook)