{
 "id": "convo_test",
 "emotion": "anger",
 "fps": 30,
 "face_frames": 221,
 "level": 4,
 "steps": 8,
 "guidance": 3.0,
 "face": "face.json",
 "body": "body.vrma",
 "audio": "audio.wav",
 "timing": {
  "face_s": 0.88,
  "body_s": 4.68,
  "total_s": 5.56
 }
}