TTS Generation

📝 통합 JSON 데이터

JSON 데이터 (characters + timeline)

{
    "characters": [
        {
            "characterId": "char_01",
            "name": "Older Detective",
            "aliases": [
            "Boss"
            ],
            "visual_traits": "Male, 50s-60s, receding hairline, white shirt, suspenders, tie, often smoking",
            "role_in_story": "Senior Investigator",
            "relationships": [
            {
                "targetId": "char_02",
                "type": "superior"
            }
            ]
        },
        {
            "characterId": "char_02",
            "name": "Younger Detective",
            "aliases": [],
            "visual_traits": "Male, 30s, dark hair, white shirt, dark vest, tie",
            "role_in_story": "Investigator",
            "relationships": [
            {
                "targetId": "char_01",
                "type": "subordinate"
            }
            ]
        }
        ],
        "timeline": [
        {
            "start": "00:00:07,000",
            "end": "00:00:10,000",
            "speaker": "Younger Detective",
            "speaker_id": "char_02",
            "original_text": "So these guys just... disappeared.",
            "tts_text": "그렇게 이 사람들은 그냥... 사라졌습니다",
            "source_type": "Voiceover",
            "context": {
            "visual": "Vintage street scene, title card 'Meridian'",
            "location": "City Street Exterior",
            "audio_mood": "Dramatic",
            "character_emotion": "Inquisitive",
            "emotion_intensity": 3,
            "relation_to_listener": "Subordinate to Superior"
            },
            "audio_layer": {
            "sfx": [],
            "bgm": {
                "mood": "Dramatic",
                "description": "Brass-heavy noir jazz intro with swelling crescendo"
            },
            "ambience": "City street bustle, distant traffic"
            }
        },
        {
            "start": "00:00:10,500",
            "end": "00:00:15,500",
            "speaker": "Older Detective",
            "speaker_id": "char_01",
            "original_text": "Yeah, along that stretch of road right above El Matador.",
            "tts_text": "그래, 엘 마타도르 바로 위 도로를 따라서 말이야.",
            "source_type": "Foreground",
            "context": {
            "visual": "Boss smoking and contemplating in dim office",
            "location": "Detective Squad Office",
            "audio_mood": "Noir",
            "character_emotion": "Contemplation",
            "emotion_intensity": 4,
            "relation_to_listener": "Superior to Subordinate"
            },
            "audio_layer": {
            "sfx": [
                {
                "type": "SFX",
                "description": "Sharp inhale of cigarette smoke",
                "timestamp": "00:00:11,500"
                },
                {
                "type": "Vocal_NonVerbal",
                "description": "Slow, heavy exhale of smoke",
                "timestamp": "00:00:13,500"
                }
            ],
            "ambience": "Quiet office room tone"
            },
            "visual_layer": {
            "action": "Smoking and contemplating",
            "facial_expression": "Grim, thoughtful, squinting through smoke",
            "body_language": "Standing, holding cigarette"
            },
            "on_screen_text": []
        },
        {
            "start": "00:00:16,000",
            "end": "00:00:17,000",
            "speaker": "Older Detective",
            "speaker_id": "char_01",
            "original_text": "You know it?",
            "tts_text": "알고 있지?",
            "source_type": "Foreground",
            "context": {
            "visual": "Younger detective listening",
            "location": "Detective Squad Office",
            "audio_mood": "Noir",
            "character_emotion": "Contemplation",
            "emotion_intensity": 4,
            "relation_to_listener": "Superior to Subordinate"
            },
            "audio_layer": {
            "sfx": [],
            "bgm": {
                "mood": "Noir",
                "description": "Subtle, low-tempo double bass and muted trumpet"
            },
            "ambience": "Quiet office room tone"
            },
            "visual_layer": {
            "action": "Listening and questioning",
            "facial_expression": "Attentive, slightly skeptical",
            "body_language": "Seated, head tilted slightly"
            },
            "on_screen_text": [
            {
                "text": "LAPD DETECTIVE SQUAD",
                "type": "signage"
            }
            ]
        },
        {
            "start": "00:00:17,000",
            "end": "00:00:18,500",
            "speaker": "Younger Detective",
            "speaker_id": "char_02",
            "original_text": "With the big rock.",
            "tts_text": "큰 바위가 있는 곳이죠.",
            "source_type": "Foreground",
            "context": {
            "visual": "Younger detective confirming location",
            "location": "Detective Squad Office",
            "audio_mood": "Noir",
            "character_emotion": "Cynicism",
            "emotion_intensity": 3,
            "relation_to_listener": "Subordinate to Superior",
            "subtext": "The big rock = Notorious crime scene/Cliff"
            },
            "audio_layer": {
            "sfx": [],
            "bgm": {
                "mood": "Noir",
                "description": "Subtle, low-tempo double bass and muted trumpet"
            },
            "ambience": "Quiet office room tone"
            },
            "visual_layer": {
            "action": "Listening and questioning",
            "facial_expression": "Attentive",
            "body_language": "Seated"
            },
            "on_screen_text": [
            {
                "text": "LAPD DETECTIVE SQUAD",
                "type": "signage"
            }
            ]
        }
        ]
}

characters와 timeline을 포함한 JSON 형식으로 입력하세요.

🎭 Lip Movement

Lip Movement (JSON 형식) 입 움직임이 있는 구간을 입력하세요. 이 구간이 발화하는 구간입니다. 각 항목은 start와 end 필드를 포함해야 합니다.

Duration 차이 허용 퍼센트 (%) 목표 duration의 몇 %까지 차이를 허용할지 설정합니다.

Duration 차이 최대값 (초) 퍼센트로 계산된 값이 이 값보다 크면 이 값으로 제한됩니다.

🎤 TTS Generation

📝 통합 JSON 데이터

🎭 Lip Movement

✨ 분석 결과