{
  "lesson": "03-realtime-voice-assistant",
  "title": "Capstone 03 — Real-Time Voice Assistant (ASR to LLM to TTS)",
  "questions": [
    {
      "stage": "pre",
      "question": "Why can a voice agent not be built by stitching three blocking REST calls?",
      "options": [
        "REST endpoints have a 30-second hard timeout",
        "REST is incompatible with WebRTC",
        "JSON serialization is too slow for audio data",
        "End-to-end latency below 800ms requires pipelined streaming at every stage"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "pre",
      "question": "What is the role of the turn-detector alongside VAD?",
      "options": [
        "Trains a custom voice clone for the agent",
        "Reads partial transcripts and scores whether the user has actually finished their utterance",
        "Detects which speaker is talking in a multi-party call",
        "Mixes background music into the output stream"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "When the user starts speaking while the agent is mid-response, what must happen for barge-in to feel right?",
      "options": [
        "The TTS finishes the current sentence before yielding",
        "The pipeline buffers user audio until TTS completes",
        "The TTS is canceled immediately, remaining LLM output is dropped, and ASR re-arms",
        "The agent raises the TTS volume to assert priority"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Why is a short filler such as \"one second, let me check\" emitted when a tool exceeds about 300ms?",
      "options": [
        "It avoids silence so the conversation does not stall while the side-channel tool runs",
        "It triggers a fallback ASR model",
        "It resets the WebRTC jitter buffer",
        "It improves WER on the next utterance"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "The first audio chunk must leave the server within roughly how long of the first LLM token?",
      "options": [
        "20ms",
        "800ms",
        "2 seconds",
        "200ms"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which metric directly measures inappropriate barge-in or over-eager turn closure?",
      "options": [
        "WER",
        "MOS",
        "Acceptance rate",
        "False-cutoff rate"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Under 3% packet loss, which two adaptive behaviors does the pipeline rely on?",
      "options": [
        "Switching to a larger LLM and disabling TTS",
        "Falling back to PSTN audio codecs",
        "Holding partial transcripts and raising the VAD speech-gate threshold",
        "Restarting the LiveKit room"
      ],
      "correct": 2,
      "explanation": ""
    }
  ]
}