THIS NEW AI VOICE MODEL IS INDISTINGUISHABLE FROM A REAL HUMAN

{
  "hook": {
    "spoken": "Jack Dorsey, the man who founded Twitter and now controls Block,",
    "ends_at": "00:04.0",
    "on_screen": "THIS NEW AI VOICE MODEL IS INDISTINGUISHABLE FROM A REAL HUMAN",
    "starts_at": "00:00.0",
    "technique": "bold_claim",
    "technique_note": "High-contrast headline hook combined with celebrity founder name-drop.",
    "why_it_stops_the_scroll": "Pairs a massive technological claim with Jack Dorsey's credible reputation."
  },
  "tags": {
    "topics": [
      "artificial intelligence",
      "tech news",
      "ai voice",
      "startups",
      "founders"
    ],
    "cta_type": "none",
    "language": "en",
    "has_music": false,
    "has_speech": true,
    "content_type": "talking_head_advice",
    "products_or_apps": [
      "Dessa",
      "Twitter",
      "Square",
      "Cash App",
      "Block",
      "ElevenLabs",
      "OpenAI"
    ],
    "has_burned_captions": true
  },
  "audio": {
    "music": "None",
    "voice": "Single young British male presenter, energetic pacing, close mic presence",
    "ambient": "Clean interior room tone with light acoustic presence",
    "mix_notes": "Clean high-gain wireless mic capture directly prioritized over quiet room noise",
    "sound_effects": "None"
  },
  "shots": [
    {
      "end": "00:06.6",
      "index": 1,
      "start": "00:00.0",
      "camera": "Front-facing smartphone camera",
      "framing": "Green screen background of Jack Dorsey, presenter keyed bottom-right",
      "movement": "Static",
      "shot_type": "medium close-up",
      "transition_in": "None / cut",
      "screen_content": "Dorsey portrait, brand icons",
      "subject_action": "Speaking to camera, gesturing with finger to points on screen",
      "what_is_visible": "Jack Dorsey photo, company logos (Twitter, Block, Square, Cash App), presenter speaking with mic",
      "duration_seconds": 6.6,
      "spoken_during_shot": "Jack Dorsey, the man who founded Twitter and now controls Block, the financial tech powerhouse behind brands like Square and Cash App,",
      "on_screen_text_during_shot": [
        "THIS NEW AI VOICE MODEL IS INDISTINGUISHABLE FROM A REAL HUMAN"
      ],
      "facial_expression_or_gesture": "Animated speaking, pointing upward"
    },
    {
      "end": "00:17.3",
      "index": 2,
      "start": "00:06.6",
      "camera": "Front-facing camera",
      "framing": "Chest-up talking head centered",
      "movement": "Handheld minor stabilization drift",
      "shot_type": "close-up",
      "transition_in": "Hard cut",
      "screen_content": "None",
      "subject_action": "Gesturing with hands, leaning toward lens to build anticipation",
      "what_is_visible": "Presenter in domestic room setting holding wireless lapel mic close to mouth",
      "duration_seconds": 10.7,
      "spoken_during_shot": "he's now taking on the likes of ElevenLabs and OpenAI, with arguably the most natural AI speech model to date. I mean, I'll play you a short snippet here because I want you to see how insane this is.",
      "on_screen_text_during_shot": [],
      "facial_expression_or_gesture": "Engaged, intense enthusiasm, pointing"
    },
    {
      "end": "00:24.8",
      "index": 3,
      "start": "00:17.3",
      "camera": "Smartphone camera",
      "framing": "Presenter keyed bottom right over dark UI demo",
      "movement": "Static",
      "shot_type": "medium close-up",
      "transition_in": "Hard cut",
      "screen_content": "Audio waveform comparison showing 'Human' and 'Dessa' speech tracks and tags",
      "subject_action": "Presenter gestures upward then listens silently as audio plays",
      "what_is_visible": "Dessa waveform audio interface, speaker labels, dialogue tags, presenter listening",
      "duration_seconds": 7.5,
      "spoken_during_shot": "Is that kind of a sore spot this year? Yeah, I can see that.",
      "on_screen_text_during_shot": [
        "Human: Winter is coming for sure, but you",
        "Dessa: Is that kind of a sore spot this year?",
        "Dessa: Yeah, I can see that."
      ],
      "facial_expression_or_gesture": "Attentive, nodding, smiling"
    },
    {
      "end": "00:58.7",
      "index": 4,
      "start": "00:24.8",
      "camera": "Front-facing camera",
      "framing": "Chest-up talking head centered",
      "movement": "Subtle handheld drift",
      "shot_type": "close-up",
      "transition_in": "Hard cut",
      "screen_content": "None",
      "subject_action": "Explaining features, counting points on fingers, emphatic hand gestures",
      "what_is_visible": "Presenter speaking directly to camera holding mic",
      "duration_seconds": 33.9,
      "spoken_during_shot": "It's called Dessa. And the craziest part of this whole story is the fact that you can run this locally on your MacBook, so it processes audio directly, it listens to you speaking, picks up on laughs and tonal shifts, and runs in real time. What does this mean? It means that the lines are getting even more blurred between what's real and what's fake. First, the man does Twitter. Next, the man reinvents financial services with Square and Block. And now he's taking on some of the biggest companies in the world to replicate your voice.",
      "on_screen_text_during_shot": [],
      "facial_expression_or_gesture": "Expressive eyebrows, broad smile, sharp emphasis"
    }
  ],
  "video": {
    "pacing": "Fast, energetic and continuous",
    "setting": "Indoor room with neutral modern interior background",
    "subject": "Young male tech presenter holding a compact wireless microphone",
    "lighting": "Even, soft direct key lighting",
    "color_grade": "Natural, clean digital smartphone grade",
    "orientation": "vertical",
    "aspect_ratio": "9:16",
    "overall_format": "talking-head",
    "tone_and_energy": "Excited, authoritative, informative",
    "duration_seconds": 58.7,
    "wardrobe_and_look": "Light grey zip-up athletic pullover, clean-shaven, short hair"
  },
  "script": [
    {
      "end": "00:03.5",
      "line": "Jack Dorsey, the man who founded Twitter and now controls Block,",
      "start": "00:00.0",
      "delivery": "Energetic, clear introductory hook delivery",
      "uncertain": false
    },
    {
      "end": "00:06.6",
      "line": "the financial tech powerhouse behind brands like Square and Cash App,",
      "start": "00:03.5",
      "delivery": "Fast explanatory cadence",
      "uncertain": false
    },
    {
      "end": "00:10.8",
      "line": "he's now taking on the likes of ElevenLabs and OpenAI,",
      "start": "00:06.6",
      "delivery": "Dramatic escalation",
      "uncertain": false
    },
    {
      "end": "00:14.3",
      "line": "with arguably the most natural AI speech model to date.",
      "start": "00:10.8",
      "delivery": "Emphatic emphasis on key words",
      "uncertain": false
    },
    {
      "end": "00:17.3",
      "line": "I mean, I'll play you a short snippet here because I want you to see how insane this is.",
      "start": "00:14.3",
      "delivery": "Conversational, direct promise of immediate proof",
      "uncertain": false
    },
    {
      "end": "00:23.0",
      "line": "Is that kind of a sore spot this year?",
      "start": "00:21.0",
      "delivery": "Sample AI audio dialogue clip",
      "uncertain": false
    },
    {
      "end": "00:24.8",
      "line": "Yeah, I can see that.",
      "start": "00:23.0",
      "delivery": "Sample audio dialogue clip response",
      "uncertain": false
    },
    {
      "end": "00:26.5",
      "line": "It's called Dessa.",
      "start": "00:24.8",
      "delivery": "Decisive, crisp announcement",
      "uncertain": false
    },
    {
      "end": "00:32.4",
      "line": "And the craziest part of this whole story is the fact that you can run this locally on your MacBook,",
      "start": "00:26.5",
      "delivery": "Excited inflection highlighting core technical differentiator",
      "uncertain": false
    },
    {
      "end": "00:40.8",
      "line": "so it processes audio directly, it listens to you speaking, picks up on laughs and tonal shifts, and runs in real time.",
      "start": "00:32.4",
      "delivery": "Rapid feature listing with rising pitch",
      "uncertain": false
    },
    {
      "end": "00:41.8",
      "line": "What does this mean?",
      "start": "00:40.8",
      "delivery": "Rhetorical transition question",
      "uncertain": false
    },
    {
      "end": "00:47.3",
      "line": "It means that the lines are getting even more blurred between what's real and what's fake.",
      "start": "00:41.8",
      "delivery": "Serious, thought-provoking impact statement",
      "uncertain": false
    },
    {
      "end": "00:49.4",
      "line": "First, the man does Twitter.",
      "start": "00:47.3",
      "delivery": "Staccato historical recap",
      "uncertain": false
    },
    {
      "end": "00:53.6",
      "line": "Next, the man reinvents financial services with Square and Block.",
      "start": "00:49.4",
      "delivery": "Rhythmic build-up",
      "uncertain": false
    },
    {
      "end": "00:58.7",
      "line": "And now he's taking on some of the biggest companies in the world to replicate your voice.",
      "start": "00:53.6",
      "delivery": "Climactic resolution, pointing right into lens",
      "uncertain": false
    }
  ],
  "editing": {
    "cut_count": 3,
    "transitions": "Direct jump cuts",
    "caption_style": "Word-by-word bold white kinetic captions at lower-center",
    "end_card_or_cta": "None",
    "average_shot_seconds": 14.7,
    "effects_and_overlays": "Green screen background cutout, animated brand logo popups"
  },
  "teardown": {
    "hook": "THIS NEW AI VOICE MODEL IS INDISTINGUISHABLE FROM A REAL HUMAN",
    "format": "talking-head",
    "mechanism": "novelty",
    "structure": [
      "Headline hook pairing Jack Dorsey with a breakthrough AI voice model.",
      "Presenter contextualizes Dorsey's market clout against ElevenLabs and OpenAI.",
      "Direct audio/visual demonstration of conversational AI nuance and laughter.",
      "Technical breakdown highlighting on-device local execution and cultural impact."
    ],
    "hook_source": "on_screen_text",
    "why_it_worked": "Anchored breakthrough tech hype to a high-profile tech founder and validated the claim with instant audio proof."
  },
  "on_screen_text": [
    {
      "end": "00:06.6",
      "kind": "hook",
      "text": "THIS NEW AI VOICE MODEL IS INDISTINGUISHABLE FROM A REAL HUMAN",
      "start": "00:00.0",
      "style": "Bold uppercase black block banner with white text and red highlighted keyword 'INDISTINGUISHABLE'",
      "source": "creator overlay",
      "position": "Top third centered"
    },
    {
      "end": "00:21.0",
      "kind": "embedded",
      "text": "Human: Winter is coming for sure, but you",
      "start": "00:18.5",
      "style": "Small white sans-serif subtitle on black UI",
      "source": "demo UI screen",
      "position": "Center lower area inside UI graphic"
    },
    {
      "end": "00:23.0",
      "kind": "embedded",
      "text": "Dessa: Is that kind of a sore spot this year?",
      "start": "00:21.0",
      "style": "Small white sans-serif text inside UI",
      "source": "demo UI screen",
      "position": "Center lower area inside UI graphic"
    },
    {
      "end": "00:24.8",
      "kind": "embedded",
      "text": "Dessa: Yeah, I can see that.",
      "start": "00:23.0",
      "style": "Small white sans-serif text inside UI",
      "source": "demo UI screen",
      "position": "Center lower area inside UI graphic"
    }
  ],
  "structure_beats": [
    {
      "end": "00:06.6",
      "beat": "Hook and Founder Context",
      "start": "00:00.0",
      "purpose": "Capture feed attention by linking Jack Dorsey to human-level AI audio."
    },
    {
      "end": "00:17.3",
      "beat": "Competitive Escalation",
      "start": "00:06.6",
      "purpose": "Frame market competition against giants OpenAI and ElevenLabs."
    },
    {
      "end": "00:24.8",
      "beat": "Audio Proof Demo",
      "start": "00:17.3",
      "purpose": "Deliver immediate tangible evidence of conversational naturalness."
    },
    {
      "end": "00:58.7",
      "beat": "Technical Value and Macro Impact",
      "start": "00:24.8",
      "purpose": "Detail local on-device execution advantages and synthesize founder legacy."
    }
  ],
  "recreation_blueprint": {
    "shot_template": [
      {
        "slot": "Shot 1",
        "visual": "Presenter cut out over founder photo and relevant company logos with top headline banner.",
        "seconds": 6.6,
        "voiceover": "Intro founder credibility, established track record, and unexpected pivot.",
        "text_overlay": "[HIGH IMPACT CLAIM ON NEW TECH CAPABILITY]"
      },
      {
        "slot": "Shot 2",
        "visual": "Direct talking head holding microphone, hyping the upcoming sample.",
        "seconds": 10.7,
        "voiceover": "Pit new product against top incumbents and set up immediate demo proof.",
        "text_overlay": "Dynamic word-by-word captions"
      },
      {
        "slot": "Shot 3",
        "visual": "Presenter green-screened over audio UI or product dashboard while sample plays.",
        "seconds": 7.5,
        "voiceover": "Sample dialogue playback featuring unique nuance or feature.",
        "text_overlay": "UI subtitle labels"
      },
      {
        "slot": "Shot 4",
        "visual": "Full-screen talking head with expressive gestures explaining deeper technical advantage.",
        "seconds": 33.9,
        "voiceover": "Explain key technical edge (e.g., local execution, speed) and recap founder trajectory.",
        "text_overlay": "Dynamic word-by-word captions"
      }
    ],
    "what_can_change": [
      "Subject topic or founder mentioned",
      "Specific software UI displayed",
      "Presenter wardrobe and background room"
    ],
    "template_summary": "High-energy tech news breakdown: founder hook -> market comparison -> quick proof demo -> technical edge recap.",
    "what_must_be_kept": [
      "Top bold headline bar in the first 6 seconds",
      "Green screen proof demo cut within the first 20 seconds",
      "Handheld mic prop style for news authenticity"
    ],
    "generation_prompts": [
      {
        "prompt": "Vertical framing, young tech journalist holding wireless microphone bottom corner, keyed over photo of tech executive with brand logos, high contrast banner at top, dynamic studio lighting.",
        "shot_index": 1,
        "negative_prompt": "Blurry, low resolution, messy key, dark scene, out of focus"
      },
      {
        "prompt": "Vertical close-up, young male creator speaking enthusiastically into camera holding wireless lapel mic, modern neutral interior room, crisp eye-level focus.",
        "shot_index": 2,
        "negative_prompt": "Overexposed, awkward expression, static, boring composition"
      },
      {
        "prompt": "Vertical split-screen UI presentation, software audio waveform interface centered on dark theme, small keyed creator listening attentively in bottom corner.",
        "shot_index": 3,
        "negative_prompt": "Cluttered graphics, unreadable UI, harsh artifacts"
      },
      {
        "prompt": "Vertical medium close-up, expressive presenter explaining complex topic with hand gestures, holding mini mic, cinematic indoor depth of field.",
        "shot_index": 4,
        "negative_prompt": "Distorted hands, blown-out highlights, shaky footage"
      }
    ]
  },
  "props_apps_and_products": [
    {
      "name": "Wireless Lavalier Microphone",
      "how_used": "Held by hand close to presenter mouth as a handheld reporting prop",
      "first_seen": "00:00.0"
    },
    {
      "name": "Dessa AI Voice Model",
      "how_used": "Shown via interface demo screenshot and played as audio proof",
      "first_seen": "00:17.3"
    }
  ]
}