Animation For Ending Video Credit

MASTER PROMPT

Vertical 9:16 cinematic product ad about AI replacing motion designers, premium startup marketing aesthetic, polished social ad pacing, high contrast dark intro, crisp typography, minimal interface visuals, clean transitions between scenes, every frame feels like a modern AI creative tools commercial built for Instagram Reels.

GLOBAL LOCK: Keep a premium ad look across the full video with vertical composition, clean motion design, sharp text legibility, restrained color palette shifting from dark blue-black intro to bright white explainer slides and then back to dark product UI scenes. Preserve a modern SaaS ad style, high clarity, smooth transitions, realistic workstation lighting in the opening shot, minimalist product-demo framing in the middle, and bold centered CTA typography at the end. No handheld camera, no messy backgrounds, no meme styling, no noisy editing.

[00:00-00:02]
A moody workstation scene shows an exhausted digital artist in a gray hoodie slumped over a desk beside a glowing desktop tower and monitor. A holographic robotic arm reaches from the computer toward the artist, implying AI takeover. The room is dim, lit by cool blue monitor glow and server light, with cinematic contrast and realistic desk clutter.

[00:02-00:04]
Hard cut to a black screen with large centered kinetic typography: “MOTION DESIGNERS LOST THEIR JOBS yesterday”. White text dominates the frame, with the word “LOST THEIR JOBS” emphasized in red and “yesterday” smaller beneath. Clean ad-style typography animation, high urgency, perfectly centered.

[00:04-00:06]
Transition to a minimal bright white background with sparse, elegant text appearing in sequence: “You can pause” and then “You can now turn a single prompt into”. The typography is airy, modern, and premium, with generous negative space and subtle motion easing.

[00:06-00:08]
The product examples begin. On a dark blurred background, a floating Dr Pepper can appears as a glossy branded ad sample, followed by a red sneaker product visual. Maintain clean commercial lighting, premium reflections, and short punchy showcase timing.

[00:08-00:10]
Cut to white interface-like screens that suggest easy website or asset generation from a prompt. Keep the composition simple, bright, and highly legible, with small UI elements and a minimalist tech-demo feel.

[00:10-00:13]
Show a dark-themed product interface labeled “Features” with stacked module cards and green check-style indicators. The UI is centered, sleek, and modern, with subtle screen glow and stable framing. This section sells capability and reliability rather than spectacle.

[00:13-00:16]
End on a black background with bold centered CTA text: “Type ‘VIBE’ in the comments to get the link”. The word “VIBE” is highlighted in cyan-blue and the phrase “to get the link” is highlighted in red. Keep the typography crisp, high-contrast, and optimized for social conversion.

NEGATIVE PROMPT

blurry text, unreadable typography, warped UI, low resolution, messy layout, random icons, extra hands, bad anatomy, jitter, flicker, noisy gradients, logo corruption, off-brand colors, shaky camera, low-contrast product shot, distorted can, distorted shoe, broken reflections, illegible CTA, subtitles, watermark, compression smearing

GLOBAL LOCK: Vertical creator-tutorial reel shot in a compact desk studio with a male presenter explaining a motion-design workflow powered by Higgsfield Vibe Motion and Claude. The host is a young adult man with light-to-medium skin, short dark hair, trimmed mustache and beard, black rectangular glasses, and a calm but excited teaching style. He wears a dark brown polo shirt, sits in a black-and-yellow gaming chair, and speaks into a gray podcast microphone mounted on a boom arm. The room has dark blue accent lighting and a creative-tech vibe. Visual inserts include Pinterest-style reference sourcing, animated typography samples, interface cards for text and motion tools, web pages referencing Anthropic/Claude and Higgsfield, and kinetic design examples. The edit uses bold on-screen captions synced word-by-word to the narration.

[00:00-00:05] Open with a stylized hook montage suggesting that this effect used to take hours. Show a high-contrast intro shot of the presenter, graphic typography, and motion-design style transitions. The pacing is fast and immediately instructional.

[00:05-00:11] Cut to the presenter in the desk studio speaking directly to camera. Word-by-word subtitles appear over his chest and the background. He explains that Vibe Motion changes the speed of motion-design work. Lips are clearly visible and should stay tightly synced.

[00:11-00:17] Show interface overlays while the presenter describes step one: scraping Pinterest or collecting visual references that match the creative vision. UI snippets and inspiration thumbnails appear around or above him. The tone is practical and workflow-oriented.

[00:17-00:23] Transition into the Vibe Motion interface with cards for text creation, animation styles, and promptable motion controls. The presenter explains that Claude helps generate full motion design from one prompt, with timing, transitions, and intensity adjustable in real time.

[00:23-00:28] Briefly show supporting web or tool pages including Anthropic/Claude and Higgsfield branding, reinforcing the stack behind the workflow. The camera remains locked on the presenter between inserts.

[00:28-00:31] Finish with the presenter’s concise takeaway and CTA to comment for the full guide. The last beat should emphasize that motion design is no longer purely manual craftsmanship; it can now be directed through prompting and quick finishing inside traditional editing tools.

GLOBAL LOCK: The video features a consistent 3D stop-motion claymation (plasticine) aesthetic. Characters are hand-molded with visible fingerprint textures and slight imperfections. The color palette is vibrant and high-contrast, using solid backgrounds of Magenta (#E91E63), Canary Yellow (#FFEB3B), and Mint Green (#A8E6CF). Lighting is bright studio-style with soft shadows. Camera is mostly static, centered, with a macro lens feel. Pacing is fast-cut (1-1.5s per shot). Speech is energetic, crisp, male-voiced, with word-by-word dynamic captions synced to the delivery.

[00:00–00:01]
A close-up of a pink clay face with a large purple mustache and wide, bulging eyes. The character looks surprised. Large white text "92% of" is centered over the face. Background is solid magenta.

[00:01–00:02]
A close-up of a red, angry-looking clay character with a brown mohawk. He is picking his nose with a pink finger. White text "are watching" appears. Background is solid yellow.

[00:02–00:03]
A blue clay portable toilet (porta-potty) spins in the center of a yellow background. White text "your videos on mute" curves around the object.

[00:03–00:05]
A green clay character shaped like the number '9' with googly eyes and thin arms. It stands in a hole on a magenta background. Text "Which means 92% of your content" appears dynamically.

[00:05–00:07]
A green and black striped clay caterpillar with red antennae crawls across a magenta background. It looks at the camera. Text "is invisible. And those static subtitle blocks?" appears.

[00:08–00:09]
A split-screen collage: Top-left shows a clay man shaving in a mirror; Bottom-left shows a clay hand holding a paintbrush; Right side shows a giant pink eye and a screaming mouth. Text "they're killing" overlays the center.

[00:09–00:10]
A yellow clay blob character wearing a purple skateboard and black boots. It has a wide-open screaming mouth. Text "your attention" appears at the bottom. Background is mint green.

[00:10–00:12]
A solid pink screen with a grainy texture. Very small, plain white sans-serif text in the center reads "boring text blob that nobody reads."

[00:13–00:14]
The yellow blob character from before is now riding the skateboard, looking happy with eyes closed. Text "Now watch this.." appears. Background is mint green.

[00:14–00:15]
Large, chunky 3D clay letters in green, yellow, and blue spell out "Word By Word" on a magenta background. The letters have a soft, squishy texture.

[00:16–00:18]
A clay character with a blue beret and mustache (a painter) holds a palette and paints a large brown 'C' on the screen. Text "color shifts, typographic reveals" appears.

[00:19–00:21]
A yellow star-shaped clay character with a face, wearing black boots and holding orange balls on its head, dances happily. Text "This is what captions should have been from the start" appears.

[00:22–00:32]
A fast-paced screen recording of a video editing software UI (InVideo). It shows various caption styles being selected and applied to videos of people talking. Text "I just found this and I'm honestly shocked it's not everywhere yet" overlays the UI.

[00:33–00:34]
A solid pink grainy screen with white text "instant cinematic text."

[00:35–00:37]
A red clay face with long purple hair and a beard looks terrified with a wide-open mouth. The character is framed by a yellow border. Text "what Save zone for TikTok and Instagram" appears.

[00:38–00:39]
A pink clay woman with long black hair sits in a yoga meditation pose on a yellow background. She looks peaceful. Text "So nothing overlaps the UI" appears.

[00:39–00:45]
More UI demonstrations showing font selection (Bangers, Bungee, etc.) and color pickers. Text "Custom fonts, full color control and the keyword styling built into the presets" overlays the screen.

[00:46–00:48]
A pink clay house that looks like a cake, decorated with a flower and candles. The name "ohneis" is on a sign. Text "This isnt a subtitle tool. This is a caption engine." appears.

[00:49–00:52]
A bunch of blue clay grapes with a green stem on a yellow background. The grapes jiggle slightly. Text "short form content and people scroll past this is why" appears.

[00:53–00:55]
Final screen: Solid pink grainy background. White text appears line-by-line: "Comment 'invideo'", "and I'll send you the link", "before this blows up."

NEGATIVE PROMPT: photorealistic, 2D animation, flat vector, smooth plastic, shiny metal, blurry textures, low contrast, dark lighting, robotic voice, static text, messy UI, jittery motion, missing limbs, distorted faces, watermark, logo.

SPEECH PACK:
[00:00–00:03] "92% of people are watching your videos on mute."
TAKE_A: (Punchy, authoritative) 92% of people... are watching your videos... on MUTE.
TAKE_B: (Shocked, fast) Did you know 92% of people watch your videos on mute?
TAKE_C: (Casual, informative) Fact: 92% of people watch your videos on mute.

[00:03–00:07] "Which means 92% of your content is invisible. And those static subtitle blocks?"
TAKE_A: Which means... 92% of your content... is INVISIBLE. And those static subtitle blocks?
TAKE_B: That means your content is basically invisible. And those boring subtitles?

[00:08–00:12] "They're killing your attention. Look at this: boring text blob that nobody reads."
TAKE_A: They're KILLING your attention. Look at this... boring text blob... that NOBODY reads.

[00:13–00:21] "Now watch this. Word-by-word animation, color shifts, typographic reveals. This is what captions should have been from the start."
TAKE_A: Now... watch THIS. Word-by-word animation! Color shifts! Typographic reveals! THIS is what captions should be.

[00:22–00:32] "I just found this and I'm honestly shocked it's not everywhere yet. It's called Dynamic Captions inside InVideo."
TAKE_A: I just found this... and I'm honestly SHOCKED it's not everywhere yet. It's called Dynamic Captions.

[00:33–00:45] "It reads your audio and turns every sentence into visual storytelling. One click, instant cinematic text."
TAKE_A: It reads your audio... and turns EVERY sentence into visual storytelling. One click. Cinematic.

[00:46–00:55] "This isn't a subtitle tool. This is a caption engine. If you're posting short-form content and people scroll past, this is why. Comment 'invideo' and I'll send you the link."
TAKE_A: This isn't a tool... it's an ENGINE. Stop the scroll. Comment 'invideo' now.

Core format and topic lock: a vertical creator tutorial showing how to create an AI VFX shot using Kling O1 inside Higgsfield, combined with Adobe After Effects and Adobe Illustrator. The main source material is a green-screen clip of the presenter walking toward camera in a white t-shirt and dark pants. The workflow then combines that green-screen footage with generated environment imagery and a bold black-and-white geometric Illustrator graphic that becomes part of the compositing transition or reveal. A male presenter in a rounded talking-head box explains each stage.

Shot-by-shot reconstruction

0.0s-14.0s
Open on the raw green-screen performance clip of the presenter facing and walking toward camera. The lower talking-head frame introduces the idea of turning this simple source footage into a polished AI VFX shot.

14.0s-28.0s
Show the workflow combination visually: the Kling green-screen video on one side, a generated environment image on the other, and a Kling O1 Edit label or module in between. This section should make clear that AI editing is being layered onto standard source footage.

28.0s-48.0s
Switch to an Illustrator-style canvas displaying a strong black-and-white radial or angular geometric graphic. The presenter explains that this designed element becomes part of the final visual transition or reveal, adding professional polish beyond the AI output alone.

48.0s-67.3s
Show the composited result, where the green-screen subject is integrated into a stylized environment with shape-based wipes or angular reveal elements. End on the final VFX shot and a CTA inviting viewers to comment “AI” for the workflow link.

Visual style
Vertical AI VFX tutorial, clean software-demo presentation, green-screen source clip, dark interface backgrounds, geometric design overlays, creator talking-head guidance, no cinematic scene changes beyond workflow steps.

Motion notes
Motion should come from transitions between source clip, workflow cards, graphic design canvas, and final composited result. Preserve the same subject identity and green-screen clip so the audience can follow the full before-to-after pipeline.

Negative prompt
messy interface, unreadable labels, unrelated effects, extra presenters, watermark, subtitles unrelated to tutorial, random footage swaps, non-geometric graphics, broken green-screen edges, non-AI workflow sections, shaky handheld filming

Speech pack
English creator narration explaining how Kling O1 Edit in Higgsfield works with green-screen footage, generated environment images, Illustrator graphics, and After Effects compositing to produce a polished VFX shot.

GLOBAL LOCK:
Subject is a Google Pixel 10 Pro XL smartphone in a premium "Champagne Gold" or "Soft Gold" finish. The phone features a distinct horizontal camera bar at the top with three visible lenses and a flash. The back is matte glass with a subtle metallic "G" logo in the center. The environment is a clean, minimalist studio setting with soft, warm, high-key lighting that creates elegant specular highlights on the phone's metallic edges. The color grade is warm, editorial, and high-contrast. Camera movement is characterized by smooth, high-speed "FPV-style" dives and zooms. Speech is a direct-to-camera instructional VO by a male creator with a warm, energetic, and clear tone, recorded with a close-mic, dry studio signature.

[00:00–00:05]
The camera starts on a hero shot of the back of the Google Pixel 10 Pro XL. It immediately performs a rapid, aggressive zoom-in (dolly-in) directly toward the USB-C charging port at the bottom of the device. As the camera "enters" the port, the scene transitions into a futuristic, dark internal environment. This internal world is filled with glowing blue and green circuit pathways, neon light streaks, and floating micro-components. The camera continues a fast, forward-moving FPV flight through these digital corridors. Lighting shifts from warm studio gold to high-contrast neon blue and black.

[00:05–00:10]
The camera rapidly zooms back out (dolly-out) from the phone, transitioning from the digital world back to the physical world. The shot settles on a medium-close-up of the male creator holding the phone in his hands. He is wearing a white and yellow striped shirt and a tan "Vans" baseball cap. He looks directly at the camera, smiling and gesturing with his hands. The background is a blurred studio setup with warm ambient lighting.
Speech: "Here's how you can make this impossible transition shot where you go inside any product using AI." (High energy, crisp articulation, lips fully visible).

[00:10–00:22]
The screen splits or overlays to show the "4 Image" requirement. Four static frames are displayed: 1. Hero phone shot, 2. Close-up of port, 3. Internal circuit world, 4. Final product shot. The creator's talking head remains at the bottom. The video then shows a screen recording of the "Google Flow" and "Google Veo 3" interface, with text prompts being entered.
Speech: "To get started, you need four images. Two of your product, one where it's about to go inside the product, and then one inside the product."

[00:22–00:43]
The visual shifts to a screen recording of Adobe After Effects. The cursor navigates through menus: "Pre-compose," then "Enable Time Remapping." The timeline shows keyframes being added and manipulated. The "Graph Editor" is shown, with the creator demonstrating how to pull the Bezier handles to create a steep speed curve.
Speech: "Once you've got these three videos here, you can simply go to Adobe After Effects. Right-click and pre-compose them. Now you can go to Layer, Time, and Enable Time Remapping. From here, you can drag your playhead across and add in a keyframe... press F9 to make them Easy Ease."

[00:43–00:52]
The final "Impossible Transition" is shown again in full screen as a result of the tutorial. Then, a second example is shown: a cinematic zoom into a Chanel No. 5 perfume bottle, traveling through the golden liquid. The video ends with the creator pointing to a "Comment AI" graphic overlay.
Speech: "And this works with any product in any niche. So if you want access to all the prompts, type AI in the comments and I'll send you a link."

NEGATIVE PROMPT:
Visual: jittery camera movement, inconsistent phone color, changing phone model, blurry textures, AI hallucinations (extra ports, weird buttons), flickering neon lights, robotic hand movements, low-resolution UI.
Speech: robotic voice, background noise, muffled audio, lip-sync mismatch, stuttering, flat delivery, harsh "S" sounds (sibilance).

SPEECH PACK:
[00:00-00:05]
(No speech, high-energy sound effect of a "whoosh" or "zoom")

[00:05-00:10]
TAKE_A: "Here's how you can make this impossible transition shot where you go inside any product using AI." (Energetic, punchy)
TAKE_B: "Want to create this impossible zoom? I'll show you how to go inside any product with AI." (Curious, inviting)
TAKE_C: "This transition looks like magic, but it's just AI. Here is the step-by-step." (Authoritative, direct)

[00:10-00:22]
TAKE_A: "To get started, you need four images. Two of your product, one where it's about to go inside, and one of the interior." (Clear, instructional)

[00:22-00:43]
TAKE_A: "In After Effects, pre-compose your clips, enable time remapping, and use the graph editor for that snap movement." (Technical, fast-paced)

[00:43-00:52]
TAKE_A: "It works for any niche! Comment AI below and I'll DM you all the prompts right now." (Urgent, CTA-focused)

Four-character cinematic montage presented as a looping stacked-panel tribute to iconic movie roles, with each horizontal band holding a different character in a stable portrait shot. Top row: a young desert messiah figure inspired by Paul Atreides, with wavy brown hair, dusty stillsuit textures, and a glowing orange sandstorm backdrop. Second row: a brooding northern warrior inspired by Jon Snow, wearing a heavy fur cloak in a cold blue-gray snowy landscape with a dragon looming behind. Third row: a black-clad cyberpunk hero inspired by Neo, standing centered in a green-tinted industrial corridor with sunglasses, trench coat, and fluorescent overhead lights. Bottom row: a chaotic clown-villain inspired by the Joker, with smeared white makeup, dark eyes, red grin, and a purple coat against blurred neon city lights at night. Keep all four characters framed in clean centered medium closeups, with subtle facial movement, slight camera breathing, and a polished cinematic poster-to-video feel. High-detail skin texture, costume accuracy, strong franchise-specific lighting, and a crisp multi-panel tribute composition.

A vertical text-only sci-fi parody intro plays over a black starfield filled with tiny white stars, styled like a classic space-opera opening crawl. Large yellow perspective text rises from the bottom of the frame and recedes into deep space, using the familiar slanted cinematic crawl layout. Near the beginning, the crawl includes a bold episode-style heading resembling “EPISODE T.H: THE TECHYOUS AWAKENS,” followed by humorous story text in the same yellow type, all moving upward in dramatic retro-futurist fashion. The sequence stays minimal: no characters, no ships, no planets, just stars and glowing yellow crawl text against black space. At the end, the intro resolves into a flat centered call-to-action card reading “FOLLOW ME AT https://www.tiktok.com/TechyHenz” in bright yellow over the same starry background. Keep the tone playful, nostalgic, and unmistakably inspired by old-school space-franchise opening crawls, with clean typography, deep perspective, and a fan-made parody energy.

MASTER PROMPT

GLOBAL LOCK: A vertical split-screen composition. The left half features a 30-year-old Caucasian woman with blonde hair tied back, wearing a chunky pink knit sweater and blue jeans, sitting by a window in a cozy cafe with warm, natural daylight. The right half features the exact same woman, wearing a plain white t-shirt, sitting at a modern desk with a silver laptop, illuminated by cool, soft office lighting. Both sides maintain photorealistic cinematic quality, 35mm lens feel, soft depth of field, and identical facial features.

[00:00–00:05] Left side: The woman sits relaxed, holding a white ceramic mug with both hands near her chest. She looks out the window to her left with a gentle, serene expression. Subtle movement in her hair and slight breathing motion. Right side: The woman is focused, looking down at the silver laptop screen, typing on the keyboard. At 00:02, she pauses typing, reaches with her right hand to pick up a grey ceramic mug on the desk, brings it to her lips to take a sip, places it back down, and resumes typing. The camera remains completely static on both sides throughout the duration. No speech.

NEGATIVE PROMPT
text, watermarks, logos, split-screen bleeding, morphing faces, inconsistent identity between left and right, unnatural hand anatomy, extra fingers, flickering lighting, temporal jitter, robotic movements, exaggerated expressions, harsh shadows, low resolution.

SHOT PROMPTS
Shot 1 (Left Side Base): A 30-year-old Caucasian woman with blonde hair tied back, wearing a chunky pink knit sweater, sitting by a window in a cozy cafe, warm natural daylight, holding a white ceramic mug, looking out the window, serene expression, cinematic, 35mm lens, soft depth of field.
Shot 2 (Right Side Base): A 30-year-old Caucasian woman with blonde hair tied back, wearing a plain white t-shirt, sitting at a modern desk typing on a silver laptop, cool soft office lighting, focused expression, cinematic, 35mm lens, soft depth of field.

SPEECH PACK
speech_present: false
transcript_segments: []
delivery_direction: N/A
mic_room_signature: N/A
sync_requirements: N/A
mix_notes: Background music only, no dialogue or voiceover.

GLOBAL LOCK: a soft 2D hand-drawn cartoon animation with clean outlines, pastel suburban color palette, gentle Studio Ghibli-inspired slice-of-life mood, an elderly man with gray-blue hair and a full beard, casual vest and shirt, a small vintage blue compact car, quiet suburban streets, dashboard flower ornament, police station / driver's license renewal office setting, smooth simple character motion, daytime lighting, no photorealism, no 3D look.

[00:00-00:05] Start outside a modest suburban house where the elderly man steps out from the porch and heads toward his small blue vintage car, calm neighborhood in the background, warm everyday cartoon atmosphere.

[00:05-00:10] Cut inside and around the car as he drives through the neighborhood, hands on the wheel, the dashboard visible with a small pink flower ornament, soft windshield reflections and passing houses establishing a slow everyday commute.

[00:10-00:16] Show exterior driving angles of the blue car moving down a quiet residential street, then approaching a police or civic-services building, keeping the animation style simple, gentle, and readable.

[00:16-00:22] Move closer to the front of the car and dashboard as he parks and reaches forward, then transition to the building entrance where he walks toward a public service counter, preserving the same cozy cartoon look.

[00:22-00:30] End in a driver's license renewal office where the elderly man speaks face-to-face with a clerk across the counter under a sign reading driver's license renewal, holding on a calm conversational exchange and mild facial reactions in a clean storybook-style cartoon frame.

NEGATIVE PROMPT: photorealism, 3D CGI, anime action style, dark noir lighting, futuristic city, luxury sports car, young protagonist, messy sketch lines, heavy shadows, horror, text-heavy graphic design, warped anatomy, crowded background, high-speed chase, dramatic explosions.

GLOBAL LOCK:
Subject: A vintage green Land Rover Defender (classic 110 model) and a modern bright orange Lamborghini Huracan.
Environment: A winding asphalt mountain road, lush green pine trees, misty background with rolling hills, overcast but bright daylight.
Consistency: Maintain the specific metallic green paint of the Land Rover and the high-gloss pearl orange of the Lamborghini.
Camera Language: Cinematic, high-speed movement, aggressive zooms, and speed ramping.
Lighting: Natural daylight with soft shadows, high-contrast metallic reflections on car bodies.
Color Grade: Earthy, desaturated greens for the Land Rover segments; high-saturation, vibrant tones for the Lamborghini segments.
Speech/Audio: Male narrator, energetic and instructional tone, clear articulation, mid-range pitch, recorded in a dry room with slight compression.

[00:00–00:02]
Visual: A wide shot of a green Land Rover Defender driving away from the camera on a mountain road. The camera rapidly zooms in toward the rear spare tire.
Action: The car is in motion; trees are blurred in the background.
Camera: Fast dolly-in/zoom.
Lighting: Soft daylight, misty atmosphere.
Speech: "Here is exactly how you can create this epic car transition..." (Narrator on-camera in PIP).

[00:02–00:04]
Visual: Extreme close-up of the Land Rover front headlight and grille. The camera "whips" to the side.
Action: Fast panning motion.
Camera: Macro lens feel, shallow depth of field.
Lighting: Glint on the glass of the headlight.

[00:04–00:06]
Visual: A "glitch" transition. The Land Rover engine bay (mechanical, dark, oily textures) morphs through a prismatic chromatic aberration effect into the green "Land Rover" oval badge.
Action: Morphing transition.
Motion: High-speed jitter and color fringing.

[00:06–00:09]
Visual: The green Land Rover badge morphs into the rear of the car. The camera pulls back to reveal the full vehicle. The creator's PIP bubble is visible in the bottom center.
Speech: "...using AI. This is such a simple effect to do, so strap in."

[00:09–00:26]
Visual: Screen recording of the Leonardo.ai interface. A cursor navigates to "Image Generation," types a prompt for "a bright orange lamborghini," and adjusts aspect ratio to 9:16.
Action: UI interaction, clicking buttons, scrolling through generated car images.
Environment: Dark mode software UI.
Speech: "To get started, you want to go to Leonardo AI. Select image on the left-hand side, write in a basic prompt... adjust the aspect ratio..."

[00:26–00:31]
Visual: Screen recording of the Kling 2.1 Video model. The user selects "Start Frame" (the wide Lamborghini) and "End Frame" (the close-up).
Action: Dragging and dropping images into the video generator slots.
Speech: "Go to video and select Kling 2.1... you can use the start and end frame."

[00:31–00:38]
Visual: Screen recording of Adobe After Effects. The "Graph Editor" shows a steep curve for speed ramping. The cursor selects "CC Force Motion Blur."
Action: Adjusting keyframes on a timeline, searching for effects in the panel.
Speech: "Bring that into a tool like Adobe After Effects with some simple speed ramping and some motion blur..."

[00:38–00:42]
Visual: Final montage of the orange Lamborghini driving fast on the mountain road, with aggressive speed ramps and motion blur. Large yellow text "AI" appears over the car.
Action: High-speed driving, camera shaking, cinematic finish.
Speech: "...to get an effect like this. If you want access to the tool, type AI in the comments."

NEGATIVE PROMPT:
Visual: Low resolution, blurry car logos, inconsistent car models (e.g., Land Rover turning into a Jeep), flickering lighting, distorted wheels, floating objects, messy UI overlays, watermark, grainy textures.
Speech: Robotic voice, background noise, echo, stuttering, muffled audio, inconsistent volume levels, lip-sync delay in PIP.

SPEECH PACK:
[00:00-00:08]
TAKE_A: "Here is exactly how you can create this epic car transition using AI. This is such a simple effect to do, so strap in." (Energetic, fast-paced)
TAKE_B: "Want to make car transitions like this? I'll show you how to use AI to do it. It's easier than you think, let's go." (Casual, inviting)
TAKE_C: "This AI car transition is going viral. Here is the step-by-step breakdown using Leonardo and Kling." (Authoritative, hook-focused)

[00:09-00:25]
TAKE_A: "To get started, go to Leonardo AI. Select image, type your prompt for the car you want, and set your aspect ratio to custom 9 by 16."
TAKE_B: "First step, head over to Leonardo. We're generating our base car images here. Make sure you get a wide shot and a close-up."

[00:26-00:42]
TAKE_A: "Now use Kling 2.1. Put your wide shot as the start and the close-up as the end. Finish it in After Effects with speed ramping and motion blur."
TAKE_B: "The secret is Kling 2.1's start and end frame feature. Then just add some CC Force Motion Blur in AE for that pro look."

Prosody Markup:
"epic car transition... (pause) ...using AI."
"strap in. (emphasis)"
"Leonardo AI (clear enunciation)"
"Kling 2.1 (punchy)"
"AI (loud, call to action)"

GLOBAL LOCK: A split-screen video format. The bottom 30% of the frame features a consistent female presenter, light brown hair, wearing a grey-to-black gradient long-sleeve top, in a minimalist white futuristic studio. The top 70% of the frame showcases various animation styles. The presenter's speech is energetic and professional. Lighting is high-key and clean.

[00:00–00:05]
TOP: A montage of rapid-fire animation clips including a mecha robot and a train station. Large yellow text: "10 Animation styles to try in Seedance 2.0".
BOTTOM: Presenter speaks directly to camera, gesturing with hands.
SPEECH: "Here are 10 animation styles you need to try in Seedance 2.0 that look like $10,000 videos."

[00:06–00:10]
TOP: Style 1: Stylized 3D. An elderly man with a blue beard and glasses in a cozy kitchen. He pours red sauce on pizza dough and then eats a slice. Soft, warm lighting.
BOTTOM: Presenter continues speaking, looking up slightly toward the top frame.
SPEECH: "Number one is stylized 3D. Looks like the opening cutscene of a game you've been playing all night."

[00:11–00:17]
TOP: Style 2: 1980s Anime. A mecha pilot in a dark helmet with red visors. Scene shifts to a giant robot walking through a snowy landscape. Grainy film texture, cool blue tones.
BOTTOM: Presenter gestures to the side.
SPEECH: "Number two is 1980s anime. That classic Japanese animation with grainy cinematic low-light we all missed."

[00:18–00:24]
TOP: Style 3: Urban 3D Anime. A group of stylish kids in Harajuku-style streetwear standing in an alley. A red sports car drifts past, kicking up dust. Vibrant, high-contrast lighting.
BOTTOM: Presenter smiles and nods.
SPEECH: "Number three is urban 3D anime. Oversized fits, chunky sneakers, and Harajuku kids. People cannot stop watching this."

[00:25–00:31]
TOP: Style 4: Illustrative 2D animation. A young boy with glasses (resembling Harry Potter) in a bustling, whimsical train station. A white owl flies toward the camera. Soft, painterly textures.
BOTTOM: Presenter speaks with enthusiasm.
SPEECH: "Number four is illustrative 2D animation. Clean editorial and rich colors. Looks like it came straight out of a children's book."

[00:32–00:38]
TOP: Style 5: Ghibli style. A wide shot of a blue-roofed castle under construction. A girl with braids walks through a field. Lush green landscapes, soft natural light.
BOTTOM: Presenter gestures broadly.
SPEECH: "Number five is Ghibli style. Come on, it's Ghibli. That timeless Miyazaki magic that makes your chest feel warm and heavy at the same time."

[00:39–00:45]
TOP: Style 6: Arcane style. A close-up of a character with glowing purple eyes. Purple energy swirls around them in a dark, gothic city. High-end cinematic VFX.
BOTTOM: Presenter looks impressed.
SPEECH: "Number six is Arcane style. Dark, gothic detail and absolutely cinematic. Looks like it cost millions of dollars to make."

[00:46–00:51]
TOP: Style 7: Pixel animation. An isometric view of a high-tech facility with yellow ambulances. Inside, two men work at a retro computer console. Flat, 16-bit aesthetic.
BOTTOM: Presenter points upward.
SPEECH: "Number seven is pixel animation. Old school gaming vibes and Super Nintendo nostalgia hitting you right in the gut."

[00:52–00:58]
TOP: Style 8: Painterly 2D animation. A silhouette of a girl against a fiery orange background. A moody shot of a house at twilight. High artistic contrast.
BOTTOM: Presenter speaks softly.
SPEECH: "Number eight is painterly 2D animation. Every single frame looks like a work of art, the kind of content people screenshot and save."

[00:59–01:04]
TOP: Style 9: Wool Stop Motion. A miniature town made of felt and wool. A felted character on a bicycle falls over. Tactile, soft textures, macro lens feel.
BOTTOM: Presenter mimics a "cozy" gesture.
SPEECH: "Number nine is wool stop motion. Handcrafted, soft, cozy like a sweater your grandma knitted."

[01:05–01:12]
TOP: Style 10: The Pixar style. A busy New York-style street with expressive, large-eyed characters. An old man looks up in awe at a rainbow light. Smooth, buttery 3D animation.
BOTTOM: Presenter gives a thumbs up.
SPEECH: "Number ten, my personal favorite: the Pixar style. That smooth, buttery 3D animation we all grew up with. Timeless and it works for every niche."

[01:13–01:16]
FULL FRAME: Presenter in the futuristic studio. Text overlay: "Comment 'AI'".
SPEECH: "Comment 'AI' to get these animation styles in your DMs."

NEGATIVE PROMPT: Visual artifacts, distorted faces, inconsistent character features, flickering lighting, blurry textures in the animation, robotic presenter movement, lip-sync mismatch, harsh audio clipping, background noise.

INVARIANTS TO LOCK
- Vertical 9:16 creator explainer Reel.
- Same young adult white male presenter with light skin, side-swept brown hair, cream sweater, black podcast microphone, framed in a rounded talking-head window near the bottom.
- Clean split layout: upper area demonstrates motion-graphics examples and product UI; lower area stays on the presenter.
- First half uses a bright white background with minimalist graphic cards; second half transitions to a dark Higgsfield interface with highlighted “Vibe Motion”.
- Tone is practical and creator-focused: motion graphics are now fast, promptable, and no longer expensive to outsource.

SHOTLIST
1. [00:00-00:06] White-background motion-graphics examples rotate rapidly: a banking-style exchange-rate widget, a celebrity-style profile card, a Netflix-looking chart, a floating to-do list, and bold typography cards like “Here’s”.
2. [00:06-00:12] The presenter continues speaking while the examples emphasize clean kinetic design, product-card movement, and crisp typography-driven animations.
3. [00:12-00:17] The layout flips into the dark Higgsfield product UI; navigation highlights the “Vibe Motion” tab as a cursor hovers over the tool.
4. [00:17-00:20] Result cards appear, including a glowing red neon Coca-Cola wordmark as a motion-graphics example.
5. [00:20-00:21] End on a bright CTA card: comment “motion” for the guide.

STYLE BIBLE
Visual style: modern creator tutorial mixed with SaaS demo.
Camera signature: static talking-head insert, eye-level medium close-up.
Lighting signature: warm soft light on presenter; upper examples are either bright high-key white mockups or dark UI screens with neon accents.
Grade signature: clean contrast, strong readability, simple color blocks, green highlight for the selected Higgsfield feature.
Speech style: energetic solo creator explanation, concise and persuasive, close-mic audio.

MASTER PROMPT
GLOBAL LOCK: Create a vertical Instagram Reel that teaches how prompt-based motion graphics can now be made quickly inside an AI tool. Keep the lower section anchored by a young adult white male presenter with side-swept brown hair, cream sweater, warm lighting, and a black microphone inside a rounded talking-head frame. Use the upper section for rapid visual proof. Begin on a bright white, minimalist motion-design showcase, then transition into a dark Higgsfield UI where the “Vibe Motion” feature is highlighted. End with a simple CTA asking viewers to comment “motion”.

[00:00-00:04] On a bright white background, cycle through several polished motion-graphics mockups: a black-and-green finance widget, a celebrity profile card, a red bar chart with a Netflix-style label, and a floating task list above a laptop. The presenter below gestures upward and explains that motion graphics used to be slow and expensive.

[00:04-00:08] Continue the white-background showcase with bold typography cards and clean UI motion examples. Keep the presenter centered below, speaking with confidence and slight urgency, emphasizing how accessible the workflow has become.

[00:08-00:13] Transition into a dark product UI. Show the Higgsfield logo and a navigation bar where “Vibe Motion” is visibly selected in green-yellow highlight. The presenter points as if naming the feature directly.

[00:13-00:18] Reveal motion-graphics outputs inside the dark interface, including a neon red Coca-Cola-style glowing script labeled “Result:”. Maintain the presenter’s lower talking-head window so the Reel still feels like a guided demo rather than a pure screen recording.

[00:18-00:21] Finish on a white CTA card with black text reading comment “motion”, paired with playful emoji-style icons. The presenter holds a direct final gesture to encourage engagement.

NEGATIVE PROMPT
Do not change the presenter identity, sweater, mic placement, or warm lighting. Avoid unreadable text, sloppy typography animation, broken brand lettering, warped neon script, muddy UI screenshots, mismatched layout spacing, or motion graphics that feel generic and random. Keep the examples crisp, minimal, and highly legible.

SPEECH PACK
[00:00-00:09] Speaker A, on camera. Meaning: motion graphics used to be slow and expensive, but now AI tools can generate them from prompts. Delivery: fast, practical, creator-first.
TAKE_A: “Motion graphics used to be one of my biggest pain points because they take forever and cost a lot to outsource.”
TAKE_B: “This kind of motion design used to be slow and expensive, and now it is becoming promptable.”
TAKE_C: “If motion graphics were your bottleneck, this is the kind of workflow that changes that.”

[00:09-00:21] Speaker A, on camera. Meaning: Higgsfield’s Vibe Motion makes it easier, and viewers can comment for the guide. Delivery: upbeat CTA.
TAKE_A: “With Higgsfield, you can create these motion graphics from a prompt, so comment motion if you want the guide.”
TAKE_B: “This is the feature I would test first, and if you want the workflow, comment motion.”
TAKE_C: “Comment motion and I will send you the link and the setup.”

Vertical showcase reel about AI-native filmmaking and creative studios, built as a fast montage of cinematic references, commercial-quality shots, studio name cards, and manifesto-style slogans. The video opens with iconic film-inspired frames and highly polished movie-like imagery, then shifts into a curated stream of ad aesthetics, dramatic portraits, stylized fashion scenes, product shots, sports action, surreal gallery visuals, and image sequences labeled with studio or creator names. Text overlays such as “GUIDED BY TASTE” and “NEW DREAM FACTORIES” frame the montage as a statement about a new generation of AI-led production companies. The overall tone should feel like a visionary industry manifesto rather than a tutorial: elegant, self-aware, image-first, and aspirational. Crisp editorial pacing, black title cards, premium cinematic grading, and a focus on taste, visual range, and the idea that AI film studios are emerging as creative brands in their own right.

GLOBAL LOCK: The subject is Maria, a young woman with long, straight blonde hair, fair skin, and a friendly expression. She wears a dark green long-sleeved top and a gold necklace. The environment alternates between a warm, indoor room with soft bokeh and a vast, cinematic Norwegian mountain landscape with green slopes and grey, jagged rock faces. The lighting is soft and warm indoors, and overcast/misty outdoors. The color grade is cinematic with desaturated greens and high contrast. Speech is clear, enthusiastic, and direct-to-camera.

[00:00–00:01]
Subject: Maria in MCU, talking directly to camera.
Environment: Indoor room, warm lighting, blurred background with framed art.
Action: Speaking with an enthusiastic expression.
Camera: Static MCU, 35mm feel, shallow depth of field.
Speech: "I created How to Train Your Dragon..."
Sync: High lip-sync strictness.

[00:01–00:03]
Subject: A massive, photorealistic white dragon (Bewilderbeast) with multiple horns and green eyes. A small figure in a yellow dress stands before it.
Environment: Epic Norwegian mountain valley, misty atmosphere, low-hanging clouds.
Action: The dragon lowers its head slowly toward the figure.
Camera: Wide shot, low angle looking up at the dragon to emphasize scale.
Lighting: Cold, natural, diffused daylight.
Motion: Subtle movement of the dragon's scales and breath mist.

[00:03–00:04]
Subject: Close-up of a hand gently touching the dark, textured snout of a dragon.
Environment: Dark, misty outdoor setting.
Action: Hand makes contact with the dragon's skin.
Camera: Extreme close-up (ECU), handheld movement.
Lighting: Moody, low-key lighting with pinkish/purple highlights.

[00:04–00:05]
Subject: Maria back in the indoor talking head setting.
Action: Smiling and gesturing with her hands.
Speech: "...in real life before Universal. And here's how I did it."

[00:05–00:09]
Subject: Montage of childhood footage (Maria on a trampoline in a blue onesie) and clips from the animated movie "How to Train Your Dragon."
Action: Child Maria doing a flip; animated characters Hiccup and Astrid riding Toothless through clouds.
Camera: Varied; UGC handheld for childhood, cinematic sweeping for movie clips.
Pacing: Fast cuts synced to the beat of the music.

[00:10–00:13]
Subject: Maria in a white summer dress, standing in the Norwegian mountains.
Environment: Grassy hillside with a massive grey rock wall in the background.
Action: Maria is seen from behind, looking at a camera on a tripod, then walking toward the rock wall.
Camera: Wide shot, static then slow pan following her movement.
Lighting: Bright, natural overcast light.

[00:14–00:22]
Subject: Screen recording of Blender 3D software.
Action: A 3D model of a dragon is being manipulated; wireframes are visible; the model is animated to rise up.
Camera: Screen capture, zooming into specific UI elements like the "Render Animation" menu.
Motion: Smooth 3D rotation and playback of the dragon's movement.

[00:23–00:28]
Subject: Compositing process in a node-based editor.
Action: Layers of "atmosphere" and "flying dragons" are added to the mountain plate.
Camera: Screen capture showing the visual progression from a raw plate to a finished VFX shot.
Motion: Small dragons flying in the background of the 3D scene.

[00:29–00:40]
Subject: Screen recording of Adobe Premiere Pro and the Artlist AI Assistant plugin.
Action: Searching for "nature" sound effects; dragging and dropping audio files into the timeline.
Camera: Close-ups on the software UI and the Artlist logo.
Speech: Explaining the sound design process and the ease of using the tool.

[00:41–00:42]
Subject: Maria back in the indoor talking head setting.
Action: Shrugging and gesturing "fast" with her hands.
Speech: "...which made the process super fast. And here's how it turned out."

[00:43–00:45]
Subject: Split-screen comparison. Top: Original movie scene. Bottom: Maria's live-action recreation.
Action: The giant dragon opens its eyes and looks at the figure in both versions simultaneously.
Camera: Static wide shots.
Sync: Perfect temporal alignment between the two clips.

[00:46–00:49]
Subject: Maria in the indoor setting, pointing toward an overlay of her YouTube channel.
Action: Inviting viewers to watch the full process.
Speech: "And you can see the full process in my latest YouTube video."
Overlay: YouTube video thumbnail "I Made Live Action How To Train Your Dragon..."

NEGATIVE PROMPT: Visual artifacts, flickering textures, inconsistent dragon anatomy, robotic human movement, blurry face, low-resolution UI, watermark (except Artlist logo where intended), unnatural lip-sync, harsh digital noise, sudden lighting jumps.

SPEECH PACK:
[00:00-00:04] "I created How to Train Your Dragon in real life before Universal. And here's how I did it."
TAKE_A: (Enthusiastic, fast-paced)
TAKE_B: (Confident, storytelling tone)
TAKE_C: (Direct, punchy)

[00:40-00:42] "Which made the process super fast. And here's how it turned out."
TAKE_A: (Excited, building anticipation)
TAKE_B: (Casual, conversational)

[00:46-00:49] "And you can see the full process in my latest YouTube video."
TAKE_A: (Warm, inviting CTA)
TAKE_B: (Helpful, informative)

GLOBAL LOCK: 9:16 vertical creator tutorial Reel, split between a young adult white male presenter in a dark warm-lit room and large screen-recorded workflow panels above or behind him. Generated visual world is a rockstar / cyberpunk action aesthetic with the same male lead wearing black sunglasses, dark jacket, chains, and leather styling, placed in fiery stage-like scenes, industrial interiors, neon-lit action frames, weapon poses, and cinematic close-ups. Interface layer shows start-frame / end-frame pairings, timeline tracks, transition bars, editing controls, artist-branded pages, audio waveform panels, prompt input fields, and media-generation cards. Keep a clear difference between the human presenter and the generated character world, while maintaining consistency within the generated character sequence.

00:00-00:08
Open with multiple start-frame and end-frame comparisons showing the same sunglasses-wearing rockstar character in fiery performance and action scenes, the presenter below points upward and speaks with high-energy tutorial cadence, timeline tracks and color bars visible on the UI, warm orange practical lighting on the presenter, gritty cinematic orange-blue grade on the generated visuals.

00:08-00:16
Continue showing side-by-side or stacked scene variations: weapon-holding poses, stage-performance close-ups, and cinematic industrial settings, while the presenter uses hand gestures to explain how the sequence is built, the UI emphasizes timeline arrangement and transition logic rather than one single prompt.

00:16-00:24
Move deeper into editing proof with zoomed-in timeline bars, frame strip details, and an `Artist` branded tool page, the presenter points at controls while explaining how to organize clips and transitions, generated character imagery remains consistent with black shades, slick styling, firelight, and action-film mood.

00:24-00:32
Show upload cards and tool menus for image-to-video or media-generation steps, then a text input field describing the scene or story, plus a cinematic preview card of the hero in a full-body action composition, visual message is that the workflow combines reference images, scene description, and motion generation inside one stack.

00:32-00:40
Display more interface states: asset slots, prompt fields, voice or audio settings, and waveform-based sound-design panels, while the presenter keeps an enthusiastic teacher rhythm, explain that the system adds sound, timing, and narrative pacing on top of the generated visual sequence.

00:40-00:48
Return to finished preview scenes featuring the rockstar/cyberpunk hero in fiery streets or industrial backdrops, then show message-like prompt cards and result panels, the presenter emphasizes how each tool layer builds toward a polished cinematic clip rather than a disconnected set of images.

00:48-01:06
Close with a dense mix of workflow proof: audio blocks, prompt cards, final preview frames, and platform-branded pages, ending on a complete cinematic result screen and conversion-oriented messaging, preserve the same sunglasses hero identity, timeline-first tutorial framing, and polished creator-education energy through the last second.

NEGATIVE PROMPT: character face drift between frames, broken sunglasses, warped guitar or weapon props, inconsistent jacket details, low-res fire effects, muddy timeline UI, unreadable tracks, broken waveform displays, random extra characters, noisy shadows, overexposed presenter skin, bad lip-sync on presenter, confusing interface hierarchy, washed-out cyberpunk colors, unstable industrial backgrounds, plastic skin, duplicate hands during gestures.

SHOT PROMPTS:
1. Start-frame / end-frame cinematic comparison card with rockstar lead in sunglasses.
2. Presenter explaining timeline-based build process in warm dark room.
3. Weapon pose and firelit stage close-up with same hero identity.
4. Zoomed-in timeline tracks and transition bars.
5. Artist-branded workflow screen.
6. Prompt input card and preview scene generator.
7. Audio waveform and sound-design panel.
8. Final polished cinematic result card with conversion CTA.

SPEECH PACK:
Single male presenter voice, medium-fast pace, excited tutorial energy, close-mic room sound, crisp articulation, frequent emphasis on workflow verbs like build, edit, animate, sound design, and generate. Lips are visible in most presenter shots and should sync tightly with upward pointing gestures. Core meaning across the timeline: here is how the cinematic sequence is constructed from start and end frames, here is the timeline and artist workflow, here is how prompts and images become motion, here is how audio is added, and here is the final polished result.

GLOBAL LOCK: vertical 9:16 glitch-core street promo, same adult male subject across all live-action shots, light skin, shaved or very closely cropped hair, black leather jacket over a white shirt, urban street with buildings on both sides, dusk or late afternoon ambient light, magenta-cyan channel split, scanlines, compression artifacts, white centered all-caps text overlays, black intertitle end card, invasive digital corruption aesthetic, no spoken dialogue, no realistic app interface, no extra characters except the unseen hand in the hand-holding shots.

[00:00-00:01] A frontal medium shot of the man standing in the middle of a city street, pointing directly toward camera with one hand. The image has magenta and cyan ghosting and visible scanlines. White centered text reads REPEAT. Camera is static, eye level, slightly telephoto. Lighting is natural dusk daylight with synthetic cyan-magenta grade layered on top.

[00:01-00:03] Cut to a shallow-focus close-up of two hands reaching and clasping in front of a softly blurred street background. Hold on the handshake or handhold for two beats. White centered text reads FEED LOOP, then repeats again on the next beat while the framing stays nearly identical. The motion is minimal and intimate, with only slight finger movement and breathing in the blur.

[00:03-00:04] Hard cut to an extreme close-up of a human eye under dense scanlines and pink-blue interference. The eye fills most of the frame and feels like a surveillance insert. No environment is visible beyond digital noise and color banding.

[00:04-00:05] Return to the clasped hands in shallow focus. White centered text now reads STAY ENGAGED. Keep the same blurred street bokeh behind the hands so the repetition feels deliberate.

[00:05-00:07] Cut to the man in profile and then three-quarter back view as he looks over his shoulder and begins to turn away down the street. White text across the center is partially corrupted and unreadable, like a broken command string. Keep the leather jacket, white shirt collar, and narrow urban lane consistent. Add chromatic offset and horizontal scanlines over the whole image.

[00:07-00:08] Cut back to the frontal pointing pose from the opening, now with a stronger glitch overlay and a corrupted white command that suggests SCROLL. The man remains expressionless, direct, and confrontational.

[00:08-00:09] Return once more to the clasped hands, now overlaid with a damaged SCROLL title and heavier distortion. The emotional meaning shifts from connection to capture.

[00:09-00:09.8] End on a black title card with subtle CRT texture and centered white text reading SCROLL. Hold steady and let the piece resolve as a command-driven end tag.

MOTION: static or near-static shots, minimal body movement, only a small pointing gesture, tiny hand motion in the clasp, a slight over-the-shoulder turn, digital jitter, scanline crawl, chromatic channel drift.

CAMERA: locked-off vertical compositions, medium portrait, macro hand shot, eye extreme close-up, over-the-shoulder street portrait, no handheld vlog energy, no sweeping cinematic movement.

LIGHTING AND GRADE: soft natural street light transformed through magenta-cyan split toning, cool black shadows, slight bloom on highlights, compressed digital texture, CRT-like scanlines.

NEGATIVE PROMPT: warm lifestyle influencer reel, smiley couple romance ad, clean corporate branding, readable real app UI, subtitles, busy crowd scenes, soft pastel fashion campaign, golden-hour travel montage, comedy expressions, cinematic drone shots, generic cyberpunk alley with neon signs everywhere.

SPEECH PACK: no speech, no narration, no lip-sync. Audio should be dark glitch ambience with low synthetic pulses, faint static, compressed hum, and impact accents on text changes.