sd2 · audio + templates

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Skin bejaan lag rahi hai? Roz face wash + SPF50 se nikhra aur protection milega. Kaleigh Beauty, ek baar try karo.

Format: Vertical 9:16, 12 seconds. Use provided images as exact assets: @Image1 is the hero product/treatment photo; @Image2 is the real vanity/studio setting and must be used for the ritual scene. Preserve the product packaging: the product is a tube (or pump-style bottle if visible) in a muted pastel color with a cylindrical/rounded shape — keep label visible but not legible. Tone / voice: Affordable Gen-Z / problem-solving, real-skin, believable improvement. Dialogue mode ON — spoken audio only (Hinglish script exactly as provided). No on-screen text generated in-scene; any tags or brand text are post only. Natural sound cues (dropper click/lather/soft towel) layered under music. Camera: vertical iPhone UGC framing, close macro and short handheld moves. No full faces; focus on cheek/hand/neck area or product application area shown in @Image1. Hard cuts between beats, realistic skin texture, subtle glow in after shot. Timecodes and beats: [0–3s] Beat 1 — Dull (first ~25%): Start with a muted, slightly desaturated close-up pulled from the aesthetic of @Image1 showing the 'before' skin state (dull, slightly textured cheek or hand) in soft, flat light. Slow 1–2 second micro-pan to show honest texture. Ambient foam/drip sound muted. No talking yet. [3–8s] Beat 2 — The ritual (middle ~40%): Hard cut into the vanity from @Image2 — warm, slightly backlit. Show the hero using the product from @Image1: one deliberate application gesture (squeeze or pump then rub between fingertips, then gentle upward strokes on cheek/hand). Include two close macros: (a) product texture on fingertips, (b) application stroke. Preserve packaging appearance exactly as described. Diegetic sounds: product click/pump and soft rubbing; music opens slightly. Voice-over (start at ~3.2s, intimate tone, only this exact line): "Skin bejaan lag rahi hai? Roz face wash + SPF50 se nikhra aur protection milega. Kaleigh Beauty, ek baar try karo." (Use natural, friendly Hinglish; sync to the ritual so words flow over the application.) [8–12s] Beat 3 — Glow (final ~35%): Hard cut back to the original framing from Beat 1. Brighter warm grade, subtle specular highlights on hydrated skin, realistic pore texture visible. Single small gesture (brush hair back or light exhale/soft smile off-camera) to sell confidence. End on a calm hold: the product from @Image1 resting next to the glowing cheek/hand in the @Image2 vanity environment for the final 0.8–1s. Music swells gently then fades. Audio notes: spoken script is the only VO; no additional spoken copy or CTAs. Keep improvement believable (hydration, subtle glow), no airbrushing or impossible changes. Avoid on-screen text, legible labels, numbers, price/claims visually. Deliver as single 12s vertical cut with hard cuts between beats.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Halka gel, halki fizz—touch karo. salicylic se dead cells hatae aur SPF suraksha, Kaleigh Beauty. Khud try karo.

Concept: Pure texture worship: extreme macro swatches of the product from @Image1 on the clean surface/palette shown in @Image2. No faces, only one anonymous fingertip and the packaging. Vertical iPhone UGC framing, soft directional light, hard rim highlights on texture, realistic skin/hand appearance. Preserve product packaging exactly: the product is a tube (or bottle if visible) with the same colour and rounded rectangular shape as shown in @Image1; label remains visible but not legible.

Style/voice: clean / dermo / science-led — calm, ingredient-forward, clinical-sensory.

Duration: 12s total. Use three macro beats with tight ASMR foreground sounds (pump/lid click, smear drag, drop crown). Subtle ambient pad underlay (~80 BPM). No on-screen text or visible CTAs in-scene; any text must be added only in post if needed.

Beats and timing (use exact timecodes):
- [0–3s] Beat 1 — Reveal (first ~25%): @Image1 product slides/rotates into macro frame on the clean surface from @Image2. One crisp mechanical sound as the lid lifts or pump clicks. Slow 0.8–1s hold on the product opening; keep label soft-focus. VO (soft, hushed Hinglish) begins at 0.8s: "Halka gel, halki fizz—touch karo."

- [3–8s] Beat 2 — The swatch (middle ~42%): two texture vignettes cut together. First vignette: fingertip drags one perfect swatch arc across the surface (gel/stretch consistent with gel physics) — amplified smear drag ASMR. Second vignette: a drop falls in slow motion and crowns, or a spatula swirls the gel into peaks; rim light makes the texture sparkle. VO continues between 3.2–7.8s: "salicylic se dead cells hatae aur SPF suraksha, Kaleigh Beauty."

- [8–12s] Beat 3 — Settle (final ~33%): product from @Image1 and the hero swatch compose into a settled flat-lay; texture glistening. One slow micro push-in (0.6–1s) ending on tactile detail (pores, gloss). Final VO line timed 9.0–11.5s: "Khud try karo." Leave last 0.5–1s for natural reverb and sound decay.

Audio/specs: foreground ASMR near-binaural: pump click/lid lift, smear drag, drop landing, spatula scrape — each cut lands on its sound. Underlay ambient pad very low. Use only the supplied spoken dialogue as the voice-over in Hinglish exactly: "Halka gel, halki fizz—touch karo. salicylic se dead cells hatae aur SPF suraksha, Kaleigh Beauty. Khud try karo." Do not add or alter spoken copy. Total spoken pacing should fit within 12s.

Technical notes/constraints: no faces, no on-screen text overlays, no readable label text in-scene, texture physics must be true-to-form, realistic skin texture on the fingertip, no impossible transformations or extra people. End on the calm flat-lay hold for post-production safe-zone overlay if required.

Image references: use @Image1 for product form/colour/packaging and @Image2 for surface/palette/background.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Aaj ka look ready—salicylic-glycolic face wash plus SPF 50 gives skin protection. Kaleigh Beauty, try it.

Concept: A 12s vertical GRWM, no-talking-on-camera UGC focused on a single hero product @Image1 with vanity setting from @Image2. Realistic Indian creator (young adult, fresh-faced skincare user) — hair clipped back, natural skin texture, subtle imperfections allowed. Preserve packaging: the product is shown as a white squeeze tube with a matte finish and rounded cap (keep label visible but not legible). Keep results believable: subtle brighter, hydrated skin.

Beats (strict timecodes):
[0–2.4s] Beat 1 — Sit-down: Creator enters frame at the vanity visible in @Image2, hair clipped back, sits facing the mirror/phone tripod. Static vertical framing, natural daylight or soft vanity light. No mouth movement. Natural diegetic sounds (mirror tap, seat shift). Spoken VO starts immediately: "Aaj ka look ready—salicylic-glycolic face wash plus SPF 50 gives skin protection. Kaleigh Beauty, try it." (VO only; face remains silent.)

[2.4–9.0s] Beat 2 — Steps run (jump-cut rhythm ~115–120 BPM): Quick jump-cut 1: small prep dab (splash of water or towel gesture) [2.4–3.3s]. Jump-cut 2 (longest close-up) [3.3–6.6s]: deliberate application with the white squeeze tube @Image1 — clear hand-to-face gesture, slow gentle lather/texture push-in macro, keep packaging visible in hand. Jump-cut 3 [6.6–7.8s]: blend/rinse-off or pat motion at the mirror, natural small adjustments (hair tuck). Keep framing consistent for snap cuts. VO continues over these cuts within the same delivered script line.

[9.0–12.0s] Beat 3 — The look (final): Hard cut to final mirror check — creator turns slightly to camera with a quiet confident half-smile (mouth closed), then looks to mirror. Place the white tube (@Image1) on the vanity (from @Image2) in-frame lower third. Hold final pose ~2.5–3s. End on natural ambient vanity sound; VO concludes within the 12s.

Camera & style notes: Vertical iPhone UGC framing, mix of medium vanity shots and a macro texture push-in for the product application. Lighting soft and flattering, no heavy beauty filters. Keep skin pores/texture visible. No on-screen text, no labels rendered legible, no additional products, no impossible skin transforms, and no model lip-syncing. Music: muted trending GRWM pop at low volume behind VO; add small diegetic taps and water sounds.

Audio requirement: Use only the supplied Hinglish spoken script exactly: "Aaj ka look ready—salicylic-glycolic face wash plus SPF 50 gives skin protection. Kaleigh Beauty, try it." Timing must fit within 12s; trim only if absolutely necessary.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

dekho aaj kya aaya—face wash aur SPF50 protection, radiant skin daily. Kaleigh Beauty. Poora set ghar le aao.

Concept
A Shelf-to-Vanity Unboxing adapted to a single-item reveal: the box arrives on a real vanity shelf and opens to present one hero item that settles center-frame; stop-motion energy, natural hands, and a final styled flat-lay close-up. Vertical UGC framing (9:16). Use @Image2 for the package and @Image3 for the vanity setting; there is no separate hero product image, so the single product will be revealed from the box and showcased with texture/application macros.

Beats (12s total)
[0–2.4s] Beat 1 — The box (first ~20%)
Top-down framing anchored to the vanity from @Image3. The box from @Image2 slides in from the left edge and stops center. Lid lifts in two crisp stop-motion pops; tissue peels back on its own. Keep hands anonymous at edges. Capture diegetic sounds: lid pop and tissue crinkle.

[2.4–7.8s] Beat 2 — Emergence & texture (middle ~45%)
Stop-motion pops: a single hero item emerges from the box and hops into place center-frame (treat @Image2 as the revealed item). Preserve the packaging shape and colour visible on the object — refer to it as “the bottle/the tube/the jar” in shots, do not rely on legible label text. After the settle-bounce, cut to a macro of the product texture and a slow application on the back of an anonymous hand or wrist (natural skin texture, believable absorption). Sound: soft tap as item lands, light ASMR for dispensing and a faint rub.

[7.8–12.0s] Beat 3 — Final flat-lay & push-in (final ~35%)
The single product glides a few centimeters into a styled flat-lay on the vanity (use small props seen in @Image3 like a sprig or towel). Hold a 1.5–2s slow push-in to the finished composition with the product dead-center and generous negative space low in frame. End on a clean loopable hold that returns visually to the closed box.

Camera & style
Vertical iPhone-style top-down UGC. Stop-motion cuts synced to a playful beat. Keep label visible but deliberately soft-focus so text is not legible. Skin shown in the application macro must be realistic with pores and natural sheen — no airbrushing.

Product preservation sentence
The revealed item is shown as the original packaging: a single tube/pump bottle/jar (preserve its form factor, colour, and shape exactly as in @Image2) — do not redesign or change the label; keep it in soft focus.

Audio & dialogue (spoken audio only)
Use the supplied Hinglish voice-over exactly as the only spoken dialogue, timed naturally to the beats and fitting within 12 seconds: "dekho aaj kya aaya—face wash aur SPF50 protection, radiant skin daily. Kaleigh Beauty. Poora set ghar le aao." Map the VO roughly: hook over [0–2.4s], value line across [2.4–7.8s], closing phrase over [7.8–12.0s]. No additional spoken CTAs or on-screen text. Layer playful plucky pop music (~100–110 BPM) under the VO and emphasise diegetic ASMR sounds (lid pop, tissue crinkle, item taps, product dispense).

Constraints & deliverables
- No on-screen text or readable label text in-scene. Post overlays are not part of this render. 
- Hands must remain anonymous and stay at edges. 
- No magical transitions, no morphing duplicates, and no instant flawless skin claims — results are subtle and believable.
- Final deliverable: a 12s, 9:16 top-down unboxing clip matching the beats above, with the exact supplied Hinglish voice-over as the only spoken dialogue, using @Image2 (package/revealed item) and @Image3 (vanity setting).

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Andar kya hai, secret: salicylic aur glycolic; daily SPF50 protection for radiant skin. Kaleigh Beauty — try karke dekho.

Concept: Ingredient Story for Kaleigh Beauty — tight, sensory macros of the raw ingredient from @Image2 that lead to the finished product reveal @Image1. Vertical UGC framing (9:16), 12 seconds total, natural skin-safe lighting, realistic textures, subtle ASMR foregrounds. Dialogue ON — use only the supplied Hinglish voice-over exactly as written.

Beats & timecodes:
[0–5s] Beat 1 — Raw (0–~45% ≈ 0–5s): Three ultra-close macro vignettes drawn from @Image2 (use the real ingredient photo as ground truth): 1) a precise split or crush shot (soft rim light, visible cellular texture), 2) a powder-fall or fine dust cascade (slow, realistic physics), 3) a slow pour or oil ribbon (viscous, glistening). Each cut is a slow push-in (0.8–1.2s per close), true-to-life motion, natural diegetic sounds (snap, hiss, liquid ribbon). No packaging, no hands beyond an anonymous fingertip if needed.

[5–8s] Beat 2 — The turn (~45–70% ≈ 5–8s): Sensory convergence — ingredient streams meet in a shallow bowl or on a neutral surface and fold into one even texture. Camera pushes in to show tactile smoothing; keep physics plausible (no morphing magic). Soft mixing sounds; VO starts here and continues through final beat.

[8–12s] Beat 3 — The bottle (~70–100% ≈ 8–12s): Hard cut to the finished product from @Image1 placed where the swirl was, same lighting world. Preserve the product’s photographed form factor, colour and shape exactly as in @Image1 (do not alter packaging). One slow orbit (about 3s) finishing on a settled hero hold (2s) with a few raw ingredient pieces artfully arranged at the base. Keep label visible but not legible; no readable text.

Camera & styling notes: vertical iPhone UGC framing, tactile macro lenses for vignettes, soft directional key light, clean neutral background, maintain Reels-safe composition (top 14% and bottom 35% clear of critical elements). Skin and touch elements must look real with natural texture.

Audio & VO (spoken-only — no additional speech): Use a warm storyteller female voice in Hinglish; pacing ~2 words/sec; no extra words. Exact script (must be the only spoken dialogue): "Andar kya hai, secret: salicylic aur glycolic; daily SPF50 protection for radiant skin. Kaleigh Beauty — try karke dekho." Align VO to start at ~5.2s (during Beat 2) and finish by ~11.5s, warm tone, conversational. Foreground ASMR: snap of split, powder hiss, liquid swirl, gentle ambient pulse (85–95 BPM). No on-screen text overlays or on-camera written claims.

Constraints: No faces or lip-syncing; no readable label text; no impossible skin results or glowing effects; hard cut to @Image1 (no morph); keep ingredient physics realistic; do not add any extra spoken CTA or brand/legal claims beyond the supplied script.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Skin ki pyaas—woh fresh feeling. salicylic ingredient, SPF se daily protection. Kaleigh Beauty. Try aur feel karo.

Concept: Product plus water, nothing else: droplets racing down the packaging, a splash crown blooming in slow motion, mist drifting through backlight — freshness coded straight into the frame. The product photo is @Image1 and the wet dark surface / setting is @Image2. Vertical 9:16, 12s total. Dialogue ON — use supplied Hinglish VO exactly as the only spoken dialogue: "Skin ki pyaas—woh fresh feeling. salicylic ingredient, SPF se daily protection. Kaleigh Beauty. Try aur feel karo." (If timing forces a tiny trim, trim only minimally; do not rewrite wording.) Spoken audio only; no on-screen text overlays or readable label text in-scene. Default camera: vertical iPhone UGC framing with clear macro on texture and application moment. Preserve packaging: the product in @Image1 is a tube-shaped white pump/tube (keep shape, color and label visible but not legible) and must not change form or duplicate. Keep skin and results believable — no faces, no full people, only the product, water, and optional simple prop (a leaf or folded towel). Natural water physics only. No floating or morphing product. Sound design focused on water ASMR; VO layered over ambient chill backing track low in mix. No CTAs as on-screen text; brand name may be spoken only inside supplied script.

Beats (12s total; 3 water events with individual cut sounds):
[0–3s] Beat 1 — First drops (first ~25%): Macro on the product from @Image1 sitting on the wet surface shown in @Image2. Condensation beads form; two or three droplets break and race down the tube in close-up. Hard backlight to silhouette each bead. Slow push-in. VO line start: "Skin ki pyaas—woh fresh feeling."
[3–8s] Beat 2 — The crown (middle ~45%): Two slow-motion set pieces, each cut on its own water sound: 1) a single drop falls beside the product and crowns on impact, 2) a thin sheet of water slides off the cap and a fine mist rolls across the frame catching the light. Keep the product stationary. VO continues: "salicylic ingredient, SPF se daily protection."
[8–12s] Beat 3 — Fresh hold (final ~30%): Mist settles; product stands glistening with droplets at rest on the tube from @Image1; place one natural prop (small leaf or folded towel) at base. Slow orbit into a calm hero hold with negative space low in frame. VO finish: "Kaleigh Beauty. Try aur feel karo." End on the settled hero hold.

Camera & art direction: vertical close macros, slow stabilized pushes and a gentle orbit; lighting cool, high-contrast backlight for bead highlights; surface from @Image2 remains visible and guides reflections. Keep label present but not legible. Use realistic water sounds for each cut; cut audio on each water event. Music: subdued ambient chill under VO (~80–90 BPM), water ASMR prominent. No on-screen text, no faces, no hands doing complex motions. Deliver final clip 12s, 9:16, with embedded VO track exactly as provided.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

7 din ka challenge, roz ek minute. salicylic aur SPF se skin glow aur protection. Kaleigh Beauty. day 1 aaj se shuru karo.

Concept:
A 12-second 7-Day Glow Journal filmed in the exact same routine corner from @Image2: a calm, science-led dermo vibe. No full faces — product/hands-focused, honest skin texture, small believable improvements across identical frames. Hero is @Image1 set beside the result each day.

Brand voice: Clean / dermo / science-led — minimal, trustworthy, ingredient-forward feeling, gentle lighting.

Setting (from @Image2): a bright, softly backlit vanity corner with neutral tiles/wood surface, towel and simple mirror edge visible. Keep ambient, clinical-wellness tones, no busy props. Use the same frame, same outfit tone, same time-of-day light for every cut.

Hero product description (preserve packaging): the product is shown as a matte white tube with a flip cap and subtle neutral accent, vertical shape preserved on the surface; label visible but not legible. Treat it as the hero item placed beside the application area in every cut.

Beats & timing (total 12s; 4 cuts representing day 1, day 3, day 5, day 7):
[0–2.4s] Beat 1 — Day 1 (first ~20%): Locked vertical framing from @Image2. A hand sets @Image1 down in the lower-right, then a slow close-in on a cheek/jawline or hand-back (no full face) showing day-1 skin honestly (visible pores, slight dullness). No camera movement; reserve upper-middle clear for post stamps. Spoken VO starts immediately: "7 din ka challenge, roz ek minute."
[2.4–8.4s] Beat 2 — Middle days (~50%): Two HARD jump cuts at ~2.4–4.8s (day 3) and ~4.8–8.4s (day 5). Identical locked framing each cut. Action: same ritual gesture repeated — a dab of product on fingertips, gentle palm pat/massage stroke into cheek or hand-back (slow, simple). Include a tight texture macro push-in (~0.5s) showing product texture absorbing, natural sheen forming. Small believable changes: skin looks slightly brighter, texture calmer, light catches a little more. Keep outfit, props, and shadow direction identical. Minimal diegetic sounds: cap click, soft pat.
[8.4–12s] Beat 3 — Day 7 (final ~30%): Hard cut to final check-in with identical framing. Gesture once more (dab + massage), then subject leans just a little closer to mirror or rests chin on hand for a private satisfied micro-reaction (eyes closed briefly, relaxed exhale; mouth closed). Hold on the product (@Image1) set beside the result for the final 0.8–1s.

Camera & style notes:
- Vertical 9:16, handheld iPhone UGC framing but locked on a tripod-equivalent steady frame — no panning, no zooms, no focus shifts across cuts except intentional texture macro push-in.
- Natural soft directional light from the same side every cut. Skin must remain realistic (pores, texture, believable sheen). No morphs, no different person between days.
- Preserve packaging shape and colour as described; keep label visible but not readable.

Audio & VO (Dialogue mode ON — spoken audio ONLY, exact script in Hinglish; do not add or change):
Spoken VO (deliver naturally, diary-entry tone, total length must fit 12s): "7 din ka challenge, roz ek minute. salicylic aur SPF se skin glow aur protection. Kaleigh Beauty. day 1 aaj se shuru karo."
Diegetic sounds: cap click, soft pat, faint mirror exhale layered under music.
Music: warm hopeful build, ~90–100 BPM, add one instrument layer per jump cut so sound grows to fullest on day 7.

On-screen text: none generated in-camera. Leave upper-middle air clear for post-production day stamps. Do not add any model-mouthed words or lip sync.

Results guidance: show subtle, believable improvement by day 7 — brighter, calmer, slightly dewier skin. No instant miracles, no tone changes, no medical claims.

Image usage:
- Use @Image2 as the locked set and framing reference for all cuts.
- Use @Image1 as the hero product placed on the surface in every cut, consistent position lower-right.

Deliverable timing checklist:
- [0–2.4s] Day 1 set-down + close-in + VO start
- [2.4–4.8s] Day 3 gesture + texture macro + VO continuation
- [4.8–8.4s] Day 5 gesture + subtle improvement + VO continuation
- [8.4–12s] Day 7 gesture + private reaction + hold on product + VO line finish

Avoid: on-screen branded text, readable label text, multiple people, changing lighting or framing, exaggerated results, mouth-synced speech.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Skin ya baal bejaan lag rahe? Yeh treatment twacha ko glow de, baal soft kare. Serenity Family Salon, book karo.

Concept: Dull → ritual-in-motion → glow. A 12s vertical (9:16) UGC-style before/after salon treatment reel filmed like an iPhone, real-feeling skin and lighting, no full face lip-syncs, only the supplied Hinglish VO as spoken audio.

Assets to use: @Image1 (hero: product / treatment photo) and @Image2 (studio / vanity photo). Use @Image2 as the physical setting (salon chair/vanity) and the hero from @Image1 as the treatment tool shown in the ritual. Preserve the product/treatment form: the product is a small pump bottle (white/neutral colour, cylindrical shape) — keep that bottle visible but never depend on legible label text.

Duration: 12 seconds total. Timecodes and beats below.

[0–3s] Beat 1 — Dull (before)
- Vertical close crop mirroring the same framing as the after: slightly desaturated, flat light. Show a believable Indian skin area (cheek/hand/neck) or dull hair ends — textured, honest skin (no full-face talking). Small, natural gestures (a fingertip showing dryness/dullness). Soft ambient room noise, minimal music filtered down.

[3–7.8s] Beat 2 — The ritual (application)
- Hard cut to the salon/vanity from @Image2. Warm light. Show the hero from @Image1 in use: a pump press or therapist hands applying treatment with two deliberate soothing motions (one macro of texture on fingertips or serum drop, one midshot of applied strokes). Keep label soft-focus; preserve pump bottle shape/colour. Include diegetic sounds: pump click, light cloth/towel. Music builds subtly.
- Spoken audio (exact Hinglish script, intimate tone, synced naturally across this beat and into the next): "Skin ya baal bejaan lag rahe? Yeh treatment twacha ko glow de, baal soft kare. Serenity Family Salon, book karo." Use only this spoken line; do not add any other speech. Ensure the full line fits into the 12s track — trim only if physically cannot fit but do not rewrite.

[7.8–12s] Beat 3 — Glow (after)
- Hard cut back to the same framing as Beat 1. Brighter, warmer grade, light catching hydrated skin or glossy hair with a small natural movement (hair swish or relaxed exhale hand). Improvement is believable — subtle glow, natural texture. End with the pump bottle from @Image1 placed beside the glowing area, held gently in frame for a 1s settle. No on-screen text generated by the camera; all label text remain unreadable.

Audio & music notes:
- Spoken audio: use only the supplied Hinglish line as voice-over (no on-screen text speech). Intimate, recommend-to-a-friend delivery. No additional VO or CTA speech.
- Music: soft R&B-lite / warm pop (95–105 BPM). Filtered thin during Beat 1, warms up through Beat 2, full at Beat 3. Add subtle diegetic sounds: pump click, fabric/towel, light fingertip contact.

Visual & style constraints:
- No full-face talking or lip-sync; focus on skin/hair/hands. Hard cuts between before→ritual→after (no morphs). Results realistic and subtle. Do not render legible label text, brand overlays, prices, medical claims, or on-screen copy. Keep skin real with visible pores and natural sheen.

Deliverable: single 12s vertical clip following the above beats, using @Image1 and @Image2 as specified, with the exact spoken script in Hinglish as the only voice-over: "Skin ya baal bejaan lag rahe? Yeh treatment twacha ko glow de, baal soft kare. Serenity Family Salon, book karo."

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

chair pe baitho, magic dekho. Hamare signature se baal mulayam aur chamkadar, confidence badhegi — Serenity Family Salon. Apna.

Concept: A 12-second vertical salon chair time-lapse for Serenity Family Salon. Locked phone-on-tripod framing showing the salon chair and station from @Image2; a single client settles in and the stylist compresses the signature service into clear hard cuts, ending on a reveal. Keep results believable and natural; skin texture real, no airbrushing. Use the supplied Hinglish voice-over exactly as spoken audio: "chair pe baitho, magic dekho. Hamare signature se baal mulayam aur chamkadar, confidence badhegi — Serenity Family Salon. Apna." Do not add or change any spoken copy. Aspect ratio: 9:16. Total duration: 12s. Dialogue mode: ON — only the supplied line, timed across beats below. Camera: vertical iPhone UGC framing, locked angle for entire clip, no moves or reframes. Use @Image2 as the chair/station background; include @Image1 on the station visible (preserve packaging): the product is shown as a small pump bottle, white with a pastel label, cylindrical pump-top shape — keep that form/colour unchanged and label visible but not legible. Client: believable Indian salon client matching face/age in provided images; same person, same outfit/hair baseline throughout; lips remain closed, no talking. Stylist hands should be natural and steady; avoid fine-detail actions that fail on render. Keep all transformations subtle and realistic (softer hair, natural shine, tidier finish). No on-screen branded text or price overlays in-scene; any time chips or salon name text must be added in post only (do not render them here). Sounds & music: upbeat build ~115 BPM; add diegetic salon textures (snips, spray hiss, brush strokes) synced so each hard cut lands on a beat. VO placement and beat map (spoken audio only): use ~2 words/sec pacing, spread across beats as below. Beats and timings: [0–2.4s] Beat 1 — Sit-down (0–20%): Locked framing on the chair/station from @Image2. Client walks in/settles, stylist places cape/towel. Show honest before state (flat/untreated hair). VO line start: first short hook phrase must begin here: "chair pe baitho, magic dekho." Include light salon ambient sound; no dialogue from client. [2.4–8.4s] Beat 2 — Progress jumps (~55%): Three hard jump cuts from the same locked angle, each landing mid-gesture showing clear stage progress: 1) stylist sections hair and prep, 2) stylist applies service steps (hands working near head; show @Image1 pump bottle on station), 3) stylist processes/refines and combs for finish. Each cut synchronized to the music beat; visible improvement at each stage. Continue VO between ~20%–75% delivering the middle of the supplied script: "Hamare signature se baal mulayam aur chamkadar, confidence badhegi — Serenity Family Salon." Keep hands and tools natural; avoid scissors near eyes and any warped hands. [8.4–12.0s] Beat 3 — Reveal turn (~25%): Hard cut to finished look; stylist gently turns the client to camera for a three-quarter reveal, client gives a quiet closed-mouth smile, stylist’s hand gives one final touch. Hold final frame for remainder of time on the result with the pump bottle from @Image1 visible at the station. Final spoken fragment (soft close) must finish within this window if any remains: "Apna." Audio/VO: use only the supplied Hinglish script, matched across the three beats as mapped; no extra CTAs. Visual style & lighting: natural salon lighting from @Image2, keep top 14% and bottom 35% clear for any post overlays; maintain consistent outfit/lighting/skin tone across cuts. Avoid impossible instant fixes, no dramatic color shifts, no plastic skin. Deliverables: single 12s vertical clip, locked static framing, supplied VO as spoken audio file, upbeat backing track with diegetic salon sounds synced to hard cuts.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

kab se break nahi liya? unka signature facial-ritual, skin glowing aur stress gaya. Serenity Family Salon. Book your hour.

Concept: Quiet, tactile salon ritual filmed as vertical UGC. Use the treatment-room photo @Image2 to set the calm, and the therapist hands photo @Image3 for all close-up touch/action. No product close-ups or labels; focus on the craft of touch, warm textiles, steam and skin texture. Keep skin realistic and the mood premium-but-warm, matching Serenity Family Salon’s in-salon vibe.

Technical: vertical 9:16; total duration 12s; default camera: handheld vertical iPhone UGC with steady, slow moves, soft directional side-light; natural skin texture maintained; avoid face focus — client shown neck-down or back-of-head only.

Audio: voice-over ONLY using this exact Hinglish script (spoken near-whisper, calm cadence): "kab se break nahi liya? unka signature facial-ritual, skin glowing aur stress gaya. Serenity Family Salon. Book your hour." Foreground ASMR SFX layered under VO: oil pour, palm glide on skin, towel press, soft exhale and distant singing-bowl tone. No other spoken lines.

Beats (use only @Image2 and @Image3 as visual sources):
[0–2.4s] Beat 1 — Set the calm
- Slow lateral pan across the prepared station in @Image2: folded warm towels, a steaming bowl or tray suggested in the frame edge, soft candle/side-light flicker. No people yet; frame shows atmosphere and hands-ready space. Audio: distant pad + single singing-bowl tone; quiet oil-pour SFX begins.

[2.4–8.4s] Beat 2 — The hands (main action)
- Tight close-ups of the therapist hands from @Image3: pour warming oil into palm (slow single pour), rub palms together in a slow circular warm, then two deliberate massage gestures — long gentle strokes along a shoulder/upper back (neck-down framing) and small fingertip circles at the temple line. Include a warm towel press and lift. Keep motions unhurried, repeated once. Camera: alternating close macro on hands-skin contact and medium close neck-down framing; maintain soft, real skin texture. Audio: SFX of oil glide, towel press, VO starts here in near-whisper following exact script pacing.

[8.4–12.0s] Beat 3 — Exhale (wind-down)
- Hands lift away slowly, towel settles back on shoulders, a visible gentle shoulder drop and a soft exhale from the client (neck-down). Hold a static shot of the serene station from @Image2 with hands placing a cloth back; linger on the calm for the final beat. Audio: finish VO line and let ambient pad + a single soft bowl tone close the clip.

Restrictions and notes:
- Do not show a client face, lips, or mouthing. No on-screen text overlays or branded captions in-frame. The supplied VO is the only spoken copy; do not add extra CTAs or wording. Keep results believable — subtle relaxed posture and a natural skin glow only. Avoid any readable label text, clinical staging, or exaggerated transformations. Keep hand motions clear and salon-safe; avoid fast cuts or chaotic camera moves.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Skin ya baalon bejaan lag rahe? Be Infinity ka ritual natural glow deti hai. Ek baar try kar ke dekho.

Concept: Dull → ritual-in-motion → glow. Vertical iPhone UGC framing, realistic Indian creator vibe (polished 25–35 working woman), honest skin texture and believable improvement. Use the provided images exactly: @Image1 is the hero product/treatment asset; @Image2 is the real vanity/studio setting. Preserve packaging: the product is a glass dropper bottle (amber glass, black dropper, cylindrical) and must remain visible but label not legible. Spoken voice-over in Hinglish must use only the supplied script. No on-screen text produced by the model; any post overlays are separate.

Total duration: 12 seconds, aspect ratio 9:16. Use hard cuts between beats. Natural, soft warm grade for Beat 2 and 3; slightly desaturated for Beat 1. Keep camera handheld-but-steady, shallow depth for texture macros. Include diegetic sounds: dropper click, skin pat, soft fabric exhale. No full face close-ups — focus on cheek/hand/neck area and product application.

Beat timing (hard cuts):
[0–3s] Beat 1 — Dull (before): Close, muted flat-lit framing showing the before state that @Image1 treats — tired/dull cheek or hand texture. Slightly desaturated, no makeup, small visible pores and natural flaws. Slow 1–2s push-in to texture, gentle sigh sound.

[3–8s] Beat 2 — The ritual (application in the provided setting): Hard cut to the vanity in @Image2. Show the amber dropper bottle from @Image1 (glass dropper bottle, amber glass, black dropper, cylindrical) being unscrewed (dropper click), 2–3 deliberate motions: one macro of 1–2 drops onto fingertips, gentle press-and-pat onto cheek or hand, and a smoothing outward stroke. Capture product texture macro as it spreads (do not over-magnify). Keep motions simple and repeatable.

Voice-over (spoken exactly, Hinglish) timed across Beat 1→Beat 3, intimate recommend-to-a-friend tone, ~2 words/sec total budget; use only this line and nothing else: "Skin ya baalon bejaan lag rahe? Be Infinity ka ritual natural glow deti hai. Ek baar try kar ke dekho." Align delivery so it finishes by the final hold; do not add extra CTAs or words.

[8–12s] Beat 3 — Glow (after): Hard cut back to the same framing as Beat 1. Slightly warmer, fuller light catching hydrated, luminous skin (subtle sheen, natural pores visible). One slow exhale gesture or gentle hair flip if hair-focused, then settle into a 1.5–2s hero hold showing the product from @Image1 placed next to the treated area on the vanity surface (label soft-focus). End on that still.

Notes/constraints: No on-screen text generated by the model, no legible label text, no impossible transformations, no full-face lip-syncing. Keep results believable and natural. Dialogue-only spoken audio must be exactly the supplied script above.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Halka sa gel ki awaaz, aloe vera se nami aur halki thandak. Be Infinity. Try karo, haath pe mehsus karo.

Format: Texture Swatch ASMR. Aspect ratio 9:16. Duration 12s. Dialogue ON — use only this exact spoken Hinglish line as voice-over (no other spoken words): "Halka sa gel ki awaaz, aloe vera se nami aur halki thandak. Be Infinity. Try karo, haath pe mehsus karo." Do not add or change the script. Vertical iPhone UGC framing. Keep lighting soft-directional, clean surface from @Image2, gentle rim highlights. Preserve the product packaging exactly as seen in @Image1: keep the bottle/jar shape, color and finish unchanged and visible but with label text soft-focus and unreadable. No faces — anonymous fingertip only. Keep skin realistic with visible texture and natural sheen. No on-screen text produced in-scene; any post overlays are outside this prompt. Sound design: near-binaural ASMR — crisp mechanical lid/pump click, fingertip smear, slow-drop crown, subtle surface drag; low ambient pad underlay ~80 BPM, very low volume. Camera: mix of extreme macro texture shots and a final flat-lay hold; cuts land on the tactile sounds. Keep results believable (hydrated, dewy finish), no instant miracle claims. Timeline and beats with exact timecodes: [0–3s] Beat 1 — Reveal: the product from @Image1 gently slides/rotates into macro frame on the clean surface from @Image2. One crisp lid lift or pump press sound synced to the cut. Macro preserves packaging shape + color. VO starts softly here with the supplied script. [3–9s] Beat 2 — The swatch (two texture vignettes): (3–6s) Finger or glass spatula drags a single perfect gel swatch arc; smear sound is prominent and synced to the VO mid-line. (6–9s) Slow-motion drop or peak formation — a drop falling and crowning or a spatula swirl that forms a glossy peak; high-frequency rim light catch. Maintain true-to-form physics (gel behaves like gel). VO continues, timing natural to the two vignettes but do not exceed total script length. [9–12s] Beat 3 — Settle: product from @Image1 and the hero swatch compose into a calm flat-lay hold, texture still glistening; one slow micro push-in close to the texture. Final breath of the VO ends within this hold. Audio: every cut hits a tactile sound (lid/pump click → smear drag → drop crown → final micro push). Avoid faces, on-screen text, legible labels, impossible textures, morphing transitions, or extra people. Output: a 12s vertical ASMR-first texture swatch video that uses @Image1 and @Image2 as specified, with the exact supplied Hinglish voice-over and synchronized tactile sounds.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Andar kya hai, wahi secret: kesar aur aloe vera. Glow aur hydration deti hai. Be Infinity — ek baar asal try karo.

Concept: Ingredient Story (single-product collapse) — extreme macros of the raw hero ingredient from @Image2, then a clean reveal of the finished product area (product not provided). Vertical UGC framing (9:16), 12s total. No faces, no hands beyond an anonymous fingertip if needed. Keep lighting natural, tactile, and Indian-warm. No on-screen text overlays, no legible label text, no brand names shown visually. Spoken voice-over (Hinglish) is the only dialogue and must be used exactly as supplied.

Beats and timings [0–12s]:
[0–5.5s] Beat 1 — Raw (first ~45%)
- 2–3 macro vignettes from @Image2: pick the most visually rich details (e.g., split leaf with gel, a close-up of saffron threads/petals, or a granular powder cascade). Each cut ~1.8–2.8s total across the vignettes. Use hard rim or directional soft light to emphasize texture (gel strings, powder fall, petal edges). Slow push-ins and subtle camera moves only; no packaging in these shots. Diegetic ASMR: split snap, powder hiss, petal flutter.
- VO timing: start VO at ~0.2s into the first vignette and continue through this beat. Voice-over line (exact, do not alter): "Andar kya hai, wahi secret: kesar aur aloe vera."

[5.5–8.5s] Beat 2 — The turn (middle ~25%)
- One short alchemical macro: ingredient streams converge — gel ribbon meeting saffron threads or powder folding into gel; camera pushes in and lingers on the smoothing texture (~3s). Keep action physically plausible, no machinery or glowing effects. Diegetic sound: a soft swirl and liquid settling.
- VO timing: continue immediately with exact line (do not alter): "Glow aur hydration deti hai."

[8.5–12s] Beat 3 — The product-area reveal (final ~30%)
- Hard cut to a clean surface where the finished product would sit (no supplied product image). Use the same lighting world as the swirl; arrange a few of the raw ingredients at the base (from @Image2) and show a tasteful macro on the texture puddle or a jar-lid area to imply the finished formula. One slow orbit and settle into a hero hold for the last 1.5–2s. No readable label text, no brand words on-screen.
- VO timing: final spoken line exactly as supplied: "Be Infinity — ek baar asal try karo." Keep tone warm, inviting, storyteller-like. End VO before the final 0.5s of the video to let the visual hold breathe.

Audio & sound guidance:
- Background: organic, earthy ambient with soft pulse (~85–95 BPM), building slightly from raw to reveal.
- Foreground: crisp diegetic ASMR per vignette (snap, hiss, flutter, swirl). Balance so VO remains clear and centered.

Creative constraints and realism:
- No on-screen text overlays or labels. Do not show faces or lip-sync. Keep skin and results believable if any skin appears (natural texture, no airbrushing). Ingredient physics must be real (no morphing, no magical particles). Hard cut into the final reveal — do not morph ingredients into a bottle.

Framing & camera defaults:
- Vertical iPhone UGC framing. Start with tight macros (extreme close-ups), then a slightly wider push-in for the turn, then a hard cut to the clean surface reveal. Keep negative space in the lower frame for potential post use but do not add overlays in-scene.

Assets to use:
- Ingredient image: @Image2 (primary visual truth for Beats 1–2). No @Image1 provided for a packaged hero — imply the finished product area without showing readable labels.

Deliverable notes:
- Duration exactly 12s. Use the exact supplied Hinglish voice-over lines as the only spoken dialogue: "Andar kya hai, wahi secret: kesar aur aloe vera. Glow aur hydration deti hai. Be Infinity — ek baar asal try karo." Do not add or alter words. No on-screen CTAs or brand text.

End.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

7 din ka challenge, roz bas ek minute. Roz lagaaya, 3 din mein glow dikha. Be Infinity. Day 1 aaj se shuru karo.

Concept
A week of small wins in identical frames: the same routine corner, same angle, same ritual gesture — day-stamped check-ins where skin improves a believable notch at a time. The unchanging frame is anchored by the hero from @Image1 (the treatment/photo asset). Vertical iPhone UGC framing, clear macro on application moments and texture, realistic skin texture and lighting.

Character & Brand Voice
Use a fresh-faced Indian Gen‑Z/early‑20s skincare creator vibe (natural, relatable). Brand voice: Affordable Gen-Z / problem-solving. Spoken language: Hinglish (see exact VO below).

Images & Preserve
- @Image1: the hero treatment/photo asset — treat as the visible hero object placed in-frame; keep label visible but not legible. Preserve its form and colour as shown.
- @Image2: routine corner photo — use this exact corner for every shot; lock framing, lighting, and composition.

Setting
Use the routine corner from @Image2. No camera movement — locked tripod/phone. Soft side light, warm morning feel. Keep upper-middle area clear for post stamps.

Duration & Beats (total 12s)
4 check-ins across the week in identical framing; each beat is a hard cut. Use diegetic sounds: cap click, palm pat, soft mirror exhale. Spoken VO only as supplied.

[0–2.4s] Beat 1 — Day 1 (first ~20%)
Locked framing on @Image2 corner. A hand gently sets the hero from @Image1 into frame (visible on the surface), then shows the subject’s cheek/jawline or hand area honestly at day‑one state. No camera move. Small ritual motion: a single dab or palm press. VO (spoken): "7 din ka challenge, roz bas ek minute." Soft cap click.

[2.4–8.4s] Beat 2 — Middle days (middle ~50%)
Three HARD jump cuts (approx equal slices) — Day 3, Day 5, Day 6 equivalents — all identical framing, same outfit and light. Each cut: repeat the same single ritual gesture (dab / massage stroke) with the hero from @Image1 visible beside the action. Show small believable improvements over cuts: slightly more skin sheen, calmer texture, tiny smoothing of pores — subtle only. Layer one additional warm instrument with each jump cut. VO continues across this section with the middle line from the script (keep pacing natural). Include soft ritual sounds (palm pat, brush pass) timed to gestures.

[8.4–12.0s] Beat 3 — Day 7 (final ~30%)
Final check-in: same framing, same ritual gesture one last time. After the gesture, the creator leans in slightly to the mirror or looks down, gives a private, relaxed exhale (mouth closed), eyes pleased. Hold the frame with the hero from @Image1 set beside the result. No exaggerated change — believable glow. VO final line: "Day 1 aaj se shuru karo." End on the quiet exhale sound; music reaches fullest warmth.

Dialogue / Voice-over (MANDATORY exact script, Hinglish)
Use this exact spoken script as the only dialogue/voice-over. Do not add or change words; keep pacing to fit 12s. If trimming is absolutely necessary to fit time, trim minimally but do not rewrite: "7 din ka challenge, roz bas ek minute. Roz lagaaya, 3 din mein glow dikha. Be Infinity. Day 1 aaj se shuru karo."

Audio & Music
Warm hopeful build (~90–100 BPM) adding one instrument layer per jump cut. Soft diegetic ritual sounds on actions. VO is recorded dry and intimate, diary-like, centered voice. No additional spoken CTAs beyond the supplied script.

On-screen text & Post
No on-screen text in-camera. Leave upper-middle clear for post stamps (day 1 / day 3 / day 5 / day 7) added in post. Do not render brand names or claims in-scene; the spoken script includes the brand mention only.

Visual Notes / Constraints
- Framing must never drift; lock angle and distance across all cuts.
- No mouthing or lip-sync on camera; VO is off-camera narration or voice-over.
- Keep skin realistic with visible pores and natural sheen; improvements subtle and believable.
- Do not show legible label text on the hero object; label can be visible but not readable.
- Use simple repeatable hand gesture (dab or palm press) — avoid fine finger work.

Deliverable
A 12-second vertical UGC video following the above beats, locked to @Image2 corner framing, with the hero object from @Image1 present in every shot, and the exact supplied Hinglish VO as the only spoken audio.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Aaj ka look ready? StudBoy ka attar perfume, der tak khushboo aur confidence. Try kar ke dekho

Concept
A hands-first, getting-ready-with-me (GRWM) in vertical UGC style filmed at the vanity from @Image2. No full-face model — focus on wrists, hands, mirror reflection details and the perfume bottle being used. Sensory, confident, real-skin textures; natural small imperfections (hair-tuck, lean to mirror). Spoken voice-over only (Hinglish) using the exact supplied script. No on-screen text generated by the talent; labels on packaging remain visible but not legible.

Beats
A 12-second video; 4 jump-cut steps timed to music beats. Use vertical phone framing, steady tripod. Keep lighting soft and warm, mirror reflection visible in background from @Image2.

[0–2.5s] Beat 1 — Sit-down / Hook
- Hands enter frame on the vanity from the bottom, placing a small 8ml perfume bottle (amber glass bottle with wooden cap, single small bottle form factor) on the vanity surface visible in the lower third. Close wrist/macros; a quick spray cap click is audible. Voice-over (spoken, no lip-sync): "Aaj ka look ready?"

[2.5–8.5s] Beat 2 — Application & sensory macro (longest, product-focused)
- Jump-cut to a close-up of a wrist and neck area in mirror reflection. Hands pick up the same 8ml perfume bottle and spray once near the neck (deliberate, elegant gesture). Macro on the mist and bottle silhouette; include a soft spray hiss sound. Show the bottle held in hand so the bottle shape, amber glass and wooden cap are clearly visible (label not legible). Voice-over continues (single take or edit-clean): "StudBoy ka attar perfume, der tak khushboo aur confidence."

[8.5–10.5s] Beat 3 — Blend / settle
- Quick jump to a natural gesture: dab or lightly pat the neck area with fingertips or a gentle hair tuck toward the sprayed spot; small mirror-check in background. Keep skin texture realistic. Subtle diegetic sounds (fabric, mirror tap). No model speech on-camera; voice-over continues if needed: "Try kar ke dekho"

[10.5–12s] Beat 4 — Final look / payoff
- Hard cut to the vanity-wide frame from @Image2 showing the bottle sitting on the vanity with the mirror behind. A hand reaches in for a confident half-smile revealed only in mirror reflection (closed mouth, minimal movement). Hold for the last beat; let the voice-over finish if timed. End on the bottle and mirror reflection.

Audio & Music
- Use a trending GRWM-pop track ~118 BPM with crisp beats so each jump-cut lands on a beat. Layer diegetic sounds: cap click, spray hiss, light fabric/hair tucks. Spoken voice-over only using this exact Hinglish script (no other speech): "Aaj ka look ready? StudBoy ka attar perfume, der tak khushboo aur confidence. Try kar ke dekho" — ensure the VO fits within 12s; trim only if physically necessary but do not change wording.

Camera & Styling notes
- Vertical iPhone UGC framing, steady tripod. Keep the vanity from @Image2 as the setting. Show the perfume as a small amber glass 8ml bottle with a wooden cap (form factor preserved). Keep skin realistic (visible pores, natural sheen). No on-screen text, no lip-sync, no face-centered speaking.

Deliverable
- 12s vertical UGC GRWM, voice-over in Hinglish exactly as supplied, focus on hands, perfume bottle application, and mirror reflection payoff. Use @Image2 for background/vanity reference.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Dekho aaj kya aaya naya attar perfume, lambi tikne wali khushboo, StudBoy se. Order karlo, apna signature banao

Concept
A shelf-to-vanity unboxing with stop-motion energy: the wooden box from @Image2 opens on a warm Indian vanity (from @Image3) and the perfume bottle from @Image1 becomes the star center-frame. Preserve the exact bottle shape and the wooden box form — label visible but unreadable.

Beats
A 12-second vertical (9:16) top-down sequence, single continuous build scaled to the vanity in @Image3.

[Beat 1 — The box; 0–2.4s]
Top-down framing on the vanity from @Image3. The wooden box from @Image2 (rectangular wooden box with hinged lid, wood grain texture) slides into frame. Stop-motion: lid lifts in two crisp steps, tissue crinkle ASMR as it parts. Anonymous hands may nudge at frame edges.

[Beat 2 — Emergence; 2.4–7.8s]
Stop-motion pops on the beat: the perfume bottle from @Image1 (8ml-style bottle: small glass bottle, cylindrical/rounded shape, visible cap — keep exact shape and colour) rises up first and largest from the box insert and hops a few centimeters into a loose grid on the vanity. A single small prop (sprig or folded linen from the vanity scene in @Image3) hops in next. Each landing has a soft glass-on-wood tap and a tiny settle-bounce.

[Beat 3 — The flat-lay; 7.8–12.0s]
Pieces glide the final centimeters into a styled flat-lay with the bottle dead-center, generous negative space low in frame. Slow 0.8s push-in to a tight macro on the bottle glass and cap; hold to let the loop feel natural. Keep the product label present but not legible; skin, hands, and props remain realistic and textured.

Camera & direction
Vertical iPhone UGC top-down framing. Stop-motion cuts timed to the music beat. Hands are anonymous, entering only at edges. No faces or lip-sync visuals.

Audio & Dialogue
Playful plucky pop / lo-fi track (~100–110 BPM) with clear beat for stop-motion pops. Diegetic sounds: lid pop, tissue crinkle, glass taps. Spoken voice-over in Hinglish (only spoken audio; no on-screen text): "Dekho aaj kya aaya naya attar perfume, lambi tikne wali khushboo, StudBoy se. Order karlo, apna signature banao" — time the VO across the emergence and final flat-lay so it fits within the 12-second cut. Do not add or change any words.

Constraints
Keep label unreadable; do not render any on-screen textual brand claims or price overlays. No magical transformations. Realistic skin and props only. Maintain the exact shapes and colours of @Image1 and @Image2 without redesigning them. Respect the vanity setting from @Image3.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Aaj ka look, saath tayaar? Main serum lagati hoon jo instant glow deta hai — Fleur Aura. Try karo, tum bhi.

Concept: Compressed GRWM, vertical iPhone UGC. No on-screen text. Off-camera Hinglish voice-over exactly: "Aaj ka look, saath tayaar? Main serum lagati hoon jo instant glow deta hai — Fleur Aura. Try karo, tum bhi." Creator stays silent (lips closed) on camera; VO is separate. Brand voice: Affordable Gen-Z, bright, relatable.

Assets: use setting photo @Image2 (vanity / mirror) as the backdrop and framing reference. No product image provided — do a hands-first, mirror-assisted application with the creator visible from chest up, hair clipped back.

Duration: 12s total. Vertical 9:16. Clear beats with jump-cuts on music beats.

Beats (with timecodes):
[0.0–2.4s] Beat 1 — Sit-down (20%): Creator walks into frame, sits at vanity from @Image2, hair clipped back, relaxed. Camera static, phone-on-tripod framing. VO starts with first phrase. Natural ambient vanity sounds.
[2.4–8.4s] Beat 2 — Steps run (middle ~50%): 3 quick jump-cuts on beats showing application routine: (1) pump/dab gesture into palm (close-up on hands + face reflected in mirror), (2) slow deliberate apply to cheeks and forehead (closest, tactile, natural skin texture visible), (3) blend upward strokes with fingers and a small hair tuck. Keep same framing and lighting across cuts. VO continues across these steps — include the exact supplied script phrase mentioning the serum and Fleur Aura. No mouthing by creator; lips remain closed.
[8.4–12.0s] Beat 3 — The look (final ~25%): Hard cut to final mirror check: creator turns slightly to camera with a quiet half-smile (mouth closed), then a last glance into the mirror; place the product bottle/pack on the vanity lower-right of frame if available (label visible but not legible). Hold final pose to 12.0s.

Camera & styling notes: vertical framing, stable tripod; soft natural/vanity light; realistic skin texture, no heavy filters. Keep motions simple and human (hair tucks, lean-ins). Avoid precise dropper counting or tiny hand choreography.

Sound & music: Trending GRWM-pop (115–125 BPM) with crisp beats for jump-cuts; subtle diegetic sounds (dab, brush tap). VO only as supplied; do not add other spoken lines.

Deliverable: 12s vertical UGC clip, 9:16, using @Image2 as the setting reference, with the exact supplied off-camera Hinglish VO and the quiet, closed-mouth on-camera performance described above.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Dekho aaj kya aaya, mini serum aur balm set, turant glow ka promise, Fleur Aura. Poora set ghar le aao.

Concept: Top-down Shelf-to-Vanity unboxing in stop-motion style using the supplied assets. Vertical iPhone UGC framing (9:16). Affordable Gen-Z, playful tone. No on-screen text; spoken Hinglish script is the only voice-over. Keep label visible but not legible; realistic skin and hands only at frame edges.

Beats (total 12s) with precise timecodes and actions:
[0.0–2.4s] Beat 1 — The box (≈20%): Top-down locked framing on the vanity from @Image3. The package from @Image2 (describe as a rectangular box with visible lid and tissue inside — preserve this packaging shape) slides into frame and rests center. Two crisp stop-motion lifts: lid opens in two quick steps; tissue crinkles and peels back on its own. Sound: lid pop and tissue rustle. VO (start immediately): "Dekho aaj kya aaya,"

[2.4–7.8s] Beat 2 — Emergence (≈45%): Stop-motion pops cut on beats. The hero item from @Image1 rises out first and largest (preserve its actual form factor, colour and shape as seen in @Image1 — the product/bottle/jar remains unchanged). A single companion piece (if present in images) follows with small hop; items settle into a loose grid. Each landing has a tiny settle-bounce with soft glass-on-wood taps. Maintain anonymous hands at edges only to nudge items if needed. VO continuing across this beat: "mini serum aur balm set, turant glow ka promise, Fleur Aura."

[7.8–12.0s] Beat 3 — The flat-lay payoff (≈35%): Pieces glide into a styled flat-lay around the hero on the vanity from @Image3; add one small prop from the scene (sprig or folded towel) tucked in last. Slow, smooth push-in towards the finished composition ending with the hero dead-center and generous negative space low in frame. Hold final frame for loop. Texture macro: one gentle edge-to-center macro to show product texture/finish (on a hand or wrist if no face present). VO final words timed to land near the end: "Poora set ghar le aao." Diegetic sounds: final soft taps, very light ambient room tone. No other spoken CTA.

Product/packaging preservation: The box from @Image2 remains a rectangular lid-style package; the hero from @Image1 remains the same form factor, colour and shape as photographed (do not redesign labels or make label text legible). If any application shot is shown, do a single simple dab on the back of a hand or wrist — slow and believable, showing slight glow/hydration only.

Audio notes: Use playful plucky pop/lo-fi (~100–110 BPM) underlying track with clear beats for the stop-motion pops; layer only the supplied Hinglish VO (exact script above) and diegetic ASMR sounds. No extra spoken lines, no on-screen text overlays, no readable label text, and no impossible skin transformations.

Final deliverable: 12s vertical stop-motion unboxing clip following the beats and timecodes above, using @Image2 for the box, @Image1 as the hero product, and the surface/setting from @Image3.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Skin ki pyaas? Nami gehri aloe se, Fleur Aura se subah tak glowing skin. Ab mehsoos karo.

Concept: Product plus water, nothing else. Use @Image1 (product photo) as the hero: a clear green round jar with a screw lid (preserve shape, colour, and label visibility but not legible). Place it on the surface shown in @Image2 (use that wet/dark surface and background lighting). Keep the shot vertical 9:16, iPhone-style UGC framing. No faces, no hands, no added people. Natural, believable water physics only. Keep skin/result language confined to the spoken script; do not add on-screen text or readable labels.

Duration: 12s total. Use three beats with water-driven moments, each cut landing on water sound. Natural ambient chill music low under foreground water ASMR.

[0.0–3.0s] Beat 1 — First drops (first ~25%)
- Framing: vertical macro push-in on @Image1 sitting on @Image2 surface. Tight on the jar's side and lid. Hard backlight from top-right to make droplets sparkle.
- Action: condensation beads form; two–three droplets break and race down the jar. Slow, tactile push-in. Sound: close, single droplet roll + soft ambient pad.
- Voice-over (start ~0.3s): speak the supplied Hinglish line with calm, hushed tone, lip-sync not needed: "Skin ki pyaas? Nami gehri aloe se, Fleur Aura se subah tak glowing skin. Ab mehsoos karo." (ensure whole line fits within 12s)

[3.0–8.5s] Beat 2 — The crown (middle ~45%)
- Two slow-motion set pieces, cut separately on sound:
  1) A single drop falls beside the jar onto the wet surface, creating a small crown splash near the base (slow-mo).
  2) A thin sheet of water slides down past the jar's lid and a fine mist drifts across the front, catching the backlight. Keep the jar stationary; water moves around it.
- Framing alternates between medium-close (showing jar + splash) and tight macro on droplets/mist. Preserve jar shape and label soft-focus.
- Sound: crown splash, sheet-slide, mist hiss layered with low ambient music. No additional spoken lines beyond the supplied script.

[8.5–12.0s] Beat 3 — Fresh hold (final ~30%)
- The mist settles. Hold on a slow orbit (gentle 25–40° arc) into a calm hero hold: jar glistening with settled droplets, one natural prop from @Image2 subtly in frame (e.g., a leaf or towel if visible in @Image2). Keep negative space low in frame.
- Sound: soft settled drip + quiet ambient tail; final cut on a single tiny droplet sound.
- No on-screen text or visual brand/claim overlays. End visually on the product hold while the spoken line finishes and trails out.

Camera & execution notes:
- Vertical 9:16, clean practical lighting that emphasizes water texture. Use shallow depth for macro details but keep the jar fully recognizable.
- Preserve product packaging exactly (clear green round jar with screw lid). Do not make label text legible or readable.
- Keep water physics realistic: no reverse gravity, no floating product, no morphing shapes.
- No faces, no hands, no added models. No on-screen text, no graphical CTAs. Voice-over is the supplied Hinglish script only, spoken softly over the water-centric sound design.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

ek chhota tour ho jaye? Glow Serum, Rose Facial, Scalp Massage — sab natural glow dete. Fleur Aura. Visit us.

Concept: One slow, confident lateral glide across the salon counter built from @Image1, revealing composed stations and a close detail — a single unbroken vertical iPhone glide, warm lights, shallow depth of field. Hands-only interactions (no faces), natural skin texture and believable results; no on-screen text, no legible labels.

Beats and timecodes (12s total, continuous glide, no visible cuts):
[0–2.4s] Beat 1 — The glide begins: camera starts at the counter edge shown in @Image1, moving laterally at walking pace, shallow DOF; warm highlights bloom ahead. VO (spoken) begins immediately: "ek chhota tour ho jaye?"

[2.4–9.0s] Beat 2 — Station stops (micro slow-downs, never fully stopping): glide eases into two soft micro-pauses. First pause frames the featured station/object from @Image2 — a composed product/station prop visible on the counter (preserve shape and color as seen in @Image2), a hand straightens or nudges it; gentle rack focus between object and background. Second pause frames the detail from @Image3 — a close texture or towel/ingredient detail, a slow hand gesture (lift a towel edge, spritz, or brush sweep). VO continues across these pauses (only this exact script): "Glow Serum, Rose Facial, Scalp Massage — sab natural glow dete." Keep all actions simple and slow so movement reads cleanly on camera.

[9.0–12.0s] Beat 3 — The full picture: the glide pulls back and widens into one composed frame of the entire counter/floor (use @Image1 composition), everything aligned, warm lights, a quiet settled hold. Final VO line (spoken): "Fleur Aura. Visit us." Hold a gentle steady drift into the 12s mark.

Audio direction: Use only the supplied spoken dialogue as voice-over in Hinglish; do not add any other spoken copy. Voice: proud-owner, confident, conversational. Underlay with soft room tone and a smooth confident groove at ~100 BPM, low-key and supportive. No chatter or additional vocalizations.

Camera & styling notes: vertical iPhone UGC framing, three-axis gimbal smooth lateral glide, shallow depth of field, soft warm lighting, natural color. Keep label text visible but not legible. No mirror reflections of the rig. Hands and station interactions only (no talking lips or additional people). Results shown are subtle and believable (natural glow, hydrated skin appearance where visible). No on-screen text, no brand or claim overlays, no magical transformations.

Deliverable: one continuous 12-second vertical clip using assets @Image1, @Image2, @Image3, matching the beat map and voice-over exactly as provided.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Andar kya hai: doodh aur aloe — gentle hydration. Narm aur araam dene wali. Barebub Milky Care cream, ek baar try.

Concept: Nature-to-bottle ingredient story. Extreme macros of the raw hero ingredient from @Image2 (use the provided ingredient photo as ground truth), then a hard cut to the finished product from @Image1. No on-screen text; spoken Hindi VO is the only dialogue provided exactly as supplied.

Beats (12s, vertical 9:16):
[0–4.8s] Beat 1 — Raw (first ~40%): Three tight macro vignettes drawn from @Image2: 1) a split or tear revealing gel strings (slow push-in, rim light); 2) a small powder or milk-like pour/fall (slow-motion, true physics); 3) a soft leaf or petal brush releasing droplets. Keep backgrounds neutral, natural textures, hard rim or directional soft light. Foreground ASMR: snap, powder hiss, petal flutter. No packaging, no hands except an anonymous fingertip if absolutely needed.

[4.8–7.8s] Beat 2 — The turn (middle ~25%): Sensory blend: camera pushes into the meeting point where droplets, gel and milk-like liquid converge into one believable, even texture. Keep motion physically plausible (no goo morphing). Maintain ASMR mix sounds. Spoken Hindi voice-over starts at 4.8s and runs through the next beats; use this exact script only: "Andar kya hai: doodh aur aloe — gentle hydration. Narm aur araam dene wali. Barebub Milky Care cream, ek baar try." No additional words, no extra CTAs.

[7.8–12.0s] Beat 3 — The bottle (final ~30%): Hard cut to the finished product shot using @Image1. Preserve packaging: a round cream jar, white (or light) color, screw-top jar shape — keep label visible but never rely on legible text. Place a few of the real raw ingredients from @Image2 arranged at the jar base. Do one slow 360° orbit or slow push-in to a settled hero hold with soft negative space. Keep skin/result claims subtle and believable (sensory hydration feel only, no exaggerated skin fixes).

Camera & style: vertical iPhone UGC framing, clean macro push-ins, natural believable textures, realistic lighting and skin/ingredient physics. Keep label soft-focus but present. No faces or talking lips, no readable on-pack copy, no numeric claims, no impossible transformations.

Sound & music: organic earthy ambient track with a soft pulse (85–95 BPM) that warms from raw to finished; foreground diegetic ASMR per vignette (snap, hiss, swirl). Spoken Hindi VO (exact script above) is the only spoken audio element; mix VO clearly over the mid/end so words are legible. Ensure total runtime is 12 seconds.

Deliverable: a 12s vertical ingredient-story video using @Image2 for all raw macros and @Image1 for the final hero shot, with the exact supplied Hindi voice-over placed as instructed.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Skin ki pyaas? Milk protein se deep hydration, Barebub Milky Care cream deti glow. Lagao, feel it on your skin

Concept: Water-focused close-up UGC for a gentle baby cream. Vertical 9:16 iPhone framing, clean dermo-leaning feel, soft cool backlight, water ASMR foreground. Use @Image1 as the hero product and @Image2 as the wet surface/setting. No faces or hands shown — product-only composition, realistic water physics, believable skin/texture implied only by product context.

Product note (must be preserved): the product is presented as a small white round jar with a screw lid and soft-matte finish — keep that jar shape, colour, and label presence visible but not legible.

Duration: 12 seconds total. Use three beats with explicit timecodes and per-cut water sounds. Spoken audio must use only the supplied Hindi script and may be trimmed only if physically impossible to fit; do not change wording.

[0–3s] Beat 1 — First drops (first ~25%)
- Shot: tight macro on @Image1 placed on the wet dark surface from @Image2. Condensation beads form on the jar. Two to three droplets break and race down the curved side of the jar in close-up. Hard backlight makes each bead a tiny lens. Slow push-in (~0.5s). Cut ON the sound of the first drop.
- VO (start ~0.2s): "Skin ki pyaas?"

[3–8.5s] Beat 2 — The crown (middle ~45%)
- Shot sequence of two slow-motion water moments around the stationary jar: (A) a single drop falls beside the jar and creates a small crown splash on the wet surface; (B) a thin sheet of water slides off the jar lid and a fine mist rolls across the frame catching the light. Keep the jar still; water performs. Cut each event on its own water impact sound. Use different shutter speeds for texture variety.
- VO (timing ~3.5s–7.5s): "Milk protein se deep hydration, Barebub Milky Care cream deti glow."

[8.5–12s] Beat 3 — Fresh hold (final ~30%)
- Shot: mist settles; jar stands glistening with resting droplets. Place one natural prop at base (soft folded muslin cloth) from the setting @Image2 to ground the scene. Slow 360-degree orbit finishing in a calm hero hold with negative space low in frame. Final cut lands on the soft hiss of mist.
- VO (timing ~9s–12s): "Lagao, feel it on your skin"

Audio & sound design:
- Background: cool ambient pad low in the mix (~80–90 BPM feel) but very subdued. Foreground: near-binaural water ASMR — droplet impacts, crown splash, sheet slide, mist hiss. Every cut syncs to a distinct water sound. The supplied Hindi script is the only spoken dialogue.

Visual constraints & guidance:
- No on-screen text overlays generated in-scene; any post-production captions are out of scope for this prompt. Do not render legible label text on the jar. No faces, no hands, no lip-sync. Keep water physics realistic (no reverse gravity, no morphing or floating product). Skin improvements are implied via hydration language only; do not show skin transformations.

Deliverable framing: vertical 9:16, 12s, use @Image1 and @Image2 as the only visual references. Ensure the jar form, colour, and round shape remain unchanged and visible throughout.

Spoken script (exact, Hindi): "Skin ki pyaas? Milk protein se deep hydration, Barebub Milky Care cream deti glow. Lagao, feel it on your skin"

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

7 din challenge, roz ek minute. Aadha hafta narm gaal, kam khujli. Barebub Milky Care cream. day 1 aaj se shuru karo.

Concept
A week of small wins in identical frames: the same routine corner, same angle, same one-minute ritual — day-stamped check-ins where skin calms and softens a believable notch at a time. Anchor each cut with the hero from @Image1 and the routine corner from @Image2.

Personality & Brand Voice
Tone: Affordable Gen-Z, gentle young parent vibe (believable Indian parent/creator). Keep skin real and textured; improvements subtle: calmer, softer, slightly more hydrated cheeks.

Product note (preserve packaging)
The product is shown as a cream in a round jar — white/pastel jar with a screw-top, short squat shape. Keep the jar visible but do not rely on readable label text.

Setting
Use @Image2 exactly: a cozy routine corner (soft natural side-light, small vanity or shelf visible). Lock camera position and framing for the full video.

Format & Framing
Vertical 9:16, iPhone UGC framing, locked tripod — no camera movement or zoom. Keep upper-middle area visually clear for post stamps.

Duration & Beats (12 seconds total)
Use four hard-cut check-ins scaled to these timecodes. Maintain identical framing, outfit, and light across cuts. Soft diegetic sounds only (cap click, palm pat), and the supplied Hindi voice-over exactly as provided.

[0.0–2.4s] Beat 1 — Day 1
Locked framing from @Image2. A hand places the cream jar from @Image1 into frame at lower-right; camera shows a cheek/jawline or the hand area at day-one state (natural texture, slight dryness or mild redness believable). No camera move. Diegetic: cap click. VO (Hindi, spoken exactly): "7 din challenge, roz ek minute."

[2.4–6.0s] Beat 2 — Day 3
Hard cut, identical framing. Repeat the same one-minute gesture: a small dab on fingertip and a gentle massage stroke on the cheek (single slow stroke). Show a tiny visual improvement: skin looks a touch less dry, softer sheen. Diegetic: soft palm pat. VO (Hindi, spoken exactly): "Aadha hafta narm gaal, kam khujli."

[6.0–8.4s] Beat 3 — Day 5
Hard cut, identical framing. Repeat the same dab-and-massage gesture. Slightly more visible calm and hydration (still realistic). Diegetic: quiet rubbing sound. VO (Hindi, spoken exactly): "Barebub Milky Care cream." (spoken once as in user script)

[8.4–12.0s] Beat 4 — Day 7 (final)
Hard cut, identical framing. Final ritual gesture one last time, then hold: the subject leans slightly toward mirror or looks down, a relaxed exhale, eyes pleased but mouth closed. The cream jar from @Image1 sits beside the result in frame. Hold final shot for payoff. Diegetic: soft settling sound. VO (Hindi, spoken exactly): "day 1 aaj se shuru karo."

Audio instructions
Dialogue mode ON. Use only this exact spoken Hindi script as voice-over: "7 din challenge, roz ek minute. Aadha hafta narm gaal, kam khujli. Barebub Milky Care cream. day 1 aaj se shuru karo." Do not add or change words. Keep voice sincere, diary-like, paced to fit 12s total (~2 words/sec average). Add a warm hopeful music bed that builds slightly across cuts (~90–100 BPM), very low in mix so the VO is clear. Include the diegetic ritual sounds per beat.

Post-production notes (for editor)
- Place day stamps (post-only) in the reserved upper-middle air: day 1 / day 3 / day 5 / day 7. No other on-screen text. 
- Do not render legible label text on the jar. 
- Keep color grading consistent; no dramatic skin smoothing or impossible changes.

Constraints reminder
No mouth-synced talking on camera (VO only). No dramatic miracle claims. Keep improvements subtle and believable. Maintain identical framing and light across all cuts.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

Chair pe baitho, magic dekho. Signature keratin treatment se baal silky aur manageable. Gloss unisex salon. Book your slot, apna din.

Concept
A 12s vertical Salon Chair Time‑Lapse filmed from one locked tripod angle: a single client settles into the salon chair and the service is compressed into three hard progress cuts — section, process, refine — ending on a quiet reveal. Use the real salon station in @Image2 as the set; keep the label visible on any product or bottle at the station but never rely on legible text. Client persona: a polished 25–35 working-age Indian woman (refer to face/pose from @Image1), natural skin texture, realistic hair thickness. Brand voice: affordable, friendly salon-next-door (Gloss unisex salon, Mumbai) — warm, approachable, problem-solving tone in visuals only. Vertical iPhone UGC framing, locked angle, natural salon lighting, realistic skin and hair results (smoother, shinier, manageable hair but believable). No on-screen text overlays; spoken script below is the only audio dialogue.

Setting
Use @Image2 as the exact set: a swivel salon chair and mirrored station with a visible tool tray and bottles; keep props and lighting constant across cuts. Maintain identical outfit, chair position and lighting for the whole take.

Beats and timecodes (total 12s)
[0–2.5s] Beat 1 — Sit-down (first ~20%)
- Framed vertically, locked tripod over-the-shoulder of the station showing the full chair and mirror from @Image2. Client from @Image1 walks in, sits, stylist places a cape/towel. Show honest before state: hair looking flat/frizzy and slightly unkempt. No lip movement. Natural salon ambience (chairs creak, faint chatter).

[2.5–9s] Beat 2 — Progress jumps (middle ~55%)
- Keep camera fixed on the same frame. Execute three HARD cuts at roughly 2s intervals: each cut lands mid-gesture showing visible progress — sectioning hair, stylist applying treatment/process (use hands, comb, spray, diffuser), processing stage with a visible timer prop or hair clip in frame, and a quick smoothing/blow-dry pass. Show tools and a bottle/jar on the tray (label visible but unreadable). Hands move confidently; motion blur on tools allowed. Maintain continuity of outfit, chair and lighting. Include subtle diegetic sounds timed to cuts (spray hiss, brush strokes, dryer hum).

[9–12s] Beat 3 — Reveal turn (final ~25%)
- Hard cut to the finished stage: stylist gently turns the client toward camera in the same chair for a 3s hold. Finished hair appears noticeably smoother, shinier, manageable (realistic). Client gives a quiet closed-mouth smile; stylist’s hand does one final settle. Hold on the result with the station and the bottle/jar still visible on the tray.

Audio / Dialogue (spoken VO only — Hinglish, exact script below; do not alter or add):
- Voice-over delivered in Hinglish, friendly salon tone, single voice timed across the video. Use the exact script and fit into 12s: "Chair pe baitho, magic dekho. Signature keratin treatment se baal silky aur manageable. Gloss unisex salon. Book your slot, apna din." Do not add extra CTAs or words.

Music & sound
- Upbeat track ~110–120 BPM that builds; every hard cut lands on the beat. Layer diegetic salon sounds (snips, spray hiss, brush/dryer) synced with the cuts.

Camera & direction notes
- Locked vertical iPhone framing; no camera moves or zooms. Hard cuts only between beats. Keep skin texture realistic, no airbrushing. No scissors near eyes; no identity drift; client never talks or mouths words. Do not show readable text on labels, mirrors, posters, or price lists.

Final shot
- Hold final frame 3s on client turned to camera, finished hair and the station from @Image2 visible; end with natural ambient sound and the final line of VO finishing.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

kab se break nahi liya? signature ritual scalp massage se stress jaata, chehra glow kare. Gloss unisex salon. Book your hour.

Format: Vertical 9:16, 12s, calm premium spa mood. Use the three provided images as follows: station/interior = @Image2 (treatment room photo), therapist hands = @Image3 (staff_hands). No full-face shots; client anonymous neck-down or back-of-head only. Keep lighting warm, soft directional side light; natural skin texture visible; label text on any bottle/towel present but not legible.

Concept (short): Serene hands-only ritual in a unisex Mumbai salon — slow close-ups, tactile ASMR, subtle visible result (relaxed posture, natural glow). Voice-over in Hinglish using the exact supplied script only.

Beats with timecodes (total 12s):
[0.0–2.4s] Beat 1 — Set the calm (20%): Slow lateral pan across the prepared station from @Image2: folded warm towels, steaming bowl or diffuser, tray with salon tools. Include hero product absence — no product macro. Ambient towel steam, faint bowl tone. VO (soft, near-whisper) begins at 0.0s: "kab se break nahi liya?"

[2.4–8.4s] Beat 2 — The hands (middle ~50%): Tight close-ups of the therapist hands from @Image3: palm-warming motion, gentle long strokes on the scalp/neck, fingertip circles at the temple, warm towel press and lift. Camera: steady vertical iPhone UGC framing, slow push-ins and lateral moves, keep every motion unhurried and repeated once. ASMR foreground: oil pour sound (quiet), palm glide, towel press. Continue VO (timed evenly across this beat) delivering: "signature ritual scalp massage se stress jaata, chehra glow kare."

[8.4–12.0s] Beat 3 — Exhale (final ~25%): Hands lift away slowly, towel settles on shoulders, visible relaxed drop of shoulders and a soft exhale. Hold on calm stationary tray / room detail from @Image2 for the final moment. Finish VO (soft, single breathy line) at ~10.5–12.0s: "Gloss unisex salon. Book your hour."

Audio & VO instructions: Use only the supplied spoken script verbatim in Hinglish. Whisper/near-whisper delivery with natural pacing to fit 12s; do not add, trim only if absolutely necessary but preserve wording. Foreground ASMR (oil pour, palm glide, towel press), background soft ambient spa pads (~60–70 BPM) and a distant singing-bowl tone. No additional spoken words, no on-screen text overlays generated in-scene.

Camera & styling notes: Vertical iPhone-style framing, close-up hand focus, avoid face framing; keep skin realistic (pores, natural sheen). No magical instant transformations; show believable relaxed posture and subtle glow. Avoid visible brand labels or readable text; keep scene tidy and non-messy.

Deliverable: single 12s vertical clip with the above beats, exact VO script: "kab se break nahi liya? signature ritual scalp massage se stress jaata, chehra glow kare. Gloss unisex salon. Book your hour."

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.

ek chhota tour ho jaye? face serum, matte lipstick, gentle cleanser — glowing skin. K.S Beauty Store. Visit karo.

Concept: One slow, confident lateral glide across the shop counter from @Image1 (counter / floor photo hero). Vertical iPhone UGC framing, continuous single gimbal glide left-to-right at walking pace, shallow depth of field, warm shop lighting, no cuts. Hands-only/objects-only action (no full-face talent). Keep scene believable and lived-in (small towels, jars, bottles or tools visible from @Image1) — labels present but never legible.

Beats (12s total, continuous move):
[0–2.4s] Beat 1 — The glide begins: start at the counter's near edge shown in @Image1, camera eases laterally. Very shallow DOF, warm lights bloom ahead. Soft room tone under music. VO (spoken, Hinglish) begins at 0s: "ek chhota tour ho jaye? face serum, matte lipstick, gentle cleanser — glowing skin. K.S Beauty Store. Visit karo." (Use this exact line only; do not add or change words.)
[2.4–9.0s] Beat 2 — Station micro-pauses: the glide eases into two micro slow-downs without hard cuts. At each pause, a hand adjusts or straightens an item drawn from the counter in @Image1 (lift a bottle, tilt a jar edge, fluff a towel). Keep focus racks between foreground and each paused subject. Maintain natural skin texture on any visible hands. VO continues distributed across this range, naming the items as the glide passes them (use only the supplied script).
[9.0–12.0s] Beat 3 — The full picture: glide pulls back to a wider composed frame of the whole counter from @Image1, everything aligned, warm lights, quiet settled hold. Gentle final cadence in VO finishes inside this hold (script concludes before 12s). No visual cuts, no speed ramps, no reversing.

Camera & shot details: vertical 9:16, smooth gimbal, consistent left-to-right direction. Keep all movements slow and fluid; no whip pans or hidden cuts. Preserve any packaging shapes visible on the counter from @Image1 — do not alter color or form. If close texture is needed, push briefly for a soft macro (no extreme tight shots that hide context).

Audio & voice: use a single spoken voice-over (Hinglish) with the exact script: "ek chhota tour ho jaye? face serum, matte lipstick, gentle cleanser — glowing skin. K.S Beauty Store. Visit karo." Tone: proud shop-owner / friendly local staff, natural, conversational, calm pacing so full script fits into 12s. Background music: smooth confident groove ~100 BPM, low bass, room tone and faint diegetic shop sounds (soft clinks, distant dryer).

Post rules & deliverables: no on-screen text overlays generated in-camera, no legible label text, no magical skin fixes, no other people talking or lip-syncing on camera. Final deliverable: continuous 12s vertical clip following beats above, with the supplied voiced script as the only spoken audio.

@Audio1 is the complete and only spoken performance for this video. The output's voice track must be this exact audio, word for word — same words, same pacing, same pronunciation. If a person is on camera while speech plays, their lips sync to @Audio1 verbatim. Do not generate, add, or substitute any other speech, narration, or voice-over. Background music stays subtle under the voice.