婴儿采访视频生成

###婴儿采访视频生成
```
{
  "shot": {
    "framing": "locked medium shot, eye-level, 50mm; Reporter LEFT holding mic, Baby RIGHT sitting on plastic stool (both visible 0-8s)",
    "camera_motion": "locked tripod"
  },
  "subjects": {
    "reporter": "beautiful female reporter from China; casual shirt; handheld mic with small mango logo/icon",
    "baby": "8-month-old baby, black eyes, chubby face; plain onesie; sitting alone on small plastic stool"
  },
  "scene": {
    "description": "street food stall area; palm trees visible in background",
    "must_show": ["palm trees in background", "plastic stool", "street/outdoor setting", "mango icon on microphone"],
    "ban": ["hospital props", "text/words on microphone", "legible text/logos anywhere", "parents", "other people in frame","overexposure"]
  },
  "timeline": [
    {
      "t": "0-4s",
      "audio_source": "Reporter",
      "mouth_state": {"Reporter": "OPEN", "Baby": "CLOSED"},
      "dialogue": [{"speaker": "Reporter", "line": "你是忙市出生的，有什么想说的吗？", "verbatim": true}]
    },
    {
      "t": "4-8s",
      "audio_source": "Baby",
      "mouth_state": {"Reporter": "CLOSED", "Baby": "OPEN (subtle lip motion)"},
      "dialogue": [{"speaker": "Baby", "line": "老板，来一套撒撇，放点涮涮辣", "verbatim": true}],
      "action": "slight camera shake at 7-8s (cameraman laughing)"
    }
  ],
  "audio": {
    "voices": [
      {"who": "Reporter", "style": "female adult from China, professional news anchor tone, exaggerated seriousness"},
      {"who": "Baby", "style": "toddler voice, high-pitched but clearly intelligible, casual confident tone"}
    ],
    "ambience": "light street noise, distant traffic",
    "music": "none",
    "effects": "muffled laughter from behind camera at 7-8s"
  },
  "rules": [
    "Reporter-left / Baby-right positioning maintained 0-8s",
    "Reporter speaks ONLY 0-4s; Baby speaks ONLY 4-8s",
    "Reporter mouth CLOSED during Baby line",
    "Baby appears to be alone (no parents visible)",
    "Microphone has ONLY mango icon, NO text",
    "Do NOT paraphrase dialogue lines",
    "Slight camera shake allowed only at 7-8s for comedy effect",
    "No overlays/subtitles/logos"
  ],
  "negatives": ["voice_swap", "misassigned_line", "paraphrase", "hospital props", "parents_visible", "text_on_microphone", "logos/text", "crowded_scene", "blurry", "excessive_shake","overexposure"]
}
```