• Step 1 (WebFetch) + Step 3 (capture_website screenshot): ~10–30s
• Step 7 (

  generate_reference_video

  ): ~3–5 min for seedance, ~5–7 min for kling
• Step 7b/c (cartoonize + retry): adds ~1–2 min if seedance moderation rejects the avatar
• Step 8 (captions): single

  add_captions

  call, ~30s–5 min (transcribe + burn in one shot)

key=value

$ARGUMENTS

Which product should the UGC ad promote? Required:

• Product URL — page to fetch for product name, category, visual references, and language

Optional:

avatar_url=

,

provider=seedance|kling

,

aspect_ratio=9:16|3:4

,

category=auto|HAUL|APP|FOOD|BEAUTY|FITNESS|TECH

,

captions=true|false

.

• If

  avatar_url

  was passed → use it as-is.
• If NOT passed → use this built-in fallback:

  https://cdn.pika.art/v2/files/agent/17d62bf9-0edb-49e4-9ba9-2c5419fa518f/seedream-1777624057811.jpeg

  Pre-generated 3D animated Pixar-style portrait of a young female creator — pre-cartoonized so seedance moderation accepts it directly, neutral enough to fit any category. Note in the final summary that the fallback was used so the caller knows to supply their own portrait for persona consistency next time.

generate_reference_video

Says: "..."

@Image1

@Image2

Says: "..."

HOOK (0–3 sec) <visual setting + creator framing + face/body cue>. Says to camera, fast and energetic: "<hook line>". <style anchor — POV handheld, authentic, raw>.

JUMP CUT 1 (3–6 sec) <wide POV — creator's body language, product partially in frame edge>. <face cue>, says fast: "<setup line>".

JUMP CUT 2 (6–9 sec) <next visual beat — could be the screen close-up showing @Image2 OR another reaction beat, depending on which beat the dialogue arc puts the reveal>. Says (or voice continues over the shot if it's a screen close-up), fast and confident: "<reveal line>".

JUMP CUT 3 (9–12 sec) <next visual beat — same logic; one of the JUMP CUTs is the screen close-up, the others are wide-POV reaction shots>. Says, fast: "<insight twist line>".

OUTRO (12–15 sec) <selfie POV, mid-chest framing, same setting>. Says to camera, fast: "<punchline line>".

avatar is image 1, asset is image 2

• Place the screen close-up on whichever JUMP CUT (1, 2, or 3) the reveal line lands on. Most ads put it on JUMP CUT 2; if the narrative needs it earlier or later, JUMP CUT 1 or JUMP CUT 3 is fine. Pick by content, not by slot number.
• The screen close-up beat shows

  @Image2

  exactly as-is and includes ONE finger-point gesture (a single finger entering from the frame edge, pointing at the hero text or product — no tap, no swipe, no scroll, no hover-on-CTA). The point gesture is the only screen interaction in the entire ad.
• The other JUMP CUTs are wide-POV reaction beats: hands stay on knees, on the bed, or at sides.

@Image2

• When to use & why: fashion, handbags, jewelry, shoes, designer drops, streetwear, luxury cosmetics with packaging story, accessories — anything where brand packaging + texture/material is the value prop. Viewers convert on vicarious-unboxing dopamine + "I just got this" social proof; texture and hardware ARE what the customer pays for, so the close-up lands on materials, not function. Not TECH (→ TECH_UNBOX), not skincare/makeup application (→ BEAUTY_APPLY).
• Sensory anchors: tissue rustle, fabric slide, hardware clinks (chains / clasps / buckles), leather/fabric grain under fingertips, foil glint.
• Setting: white unmade bed in natural window light; bathroom mirror in background for the outro held-up reveal; streetwear drops may use desk/floor.
• Close-up beat device: NOT a screen — product close-up.

  @Image2

  is a product photo (or brand-site mobile view); the single finger-point lands on a hardware detail (chain, clasp, embossed logo).
• Dialogue character: hook is mystery tease — frame the unboxing as something the viewer doesn't yet know the contents of; do NOT name the product in the hook line. Arc: hook the unboxing mystery → brand name + drop context → reveal the material/silhouette while close-up holds on hardware → tactile/wearability insight (how it feels on the body) → punchline that invites the viewer to imagine themselves with the artifact.

• When to use & why: SaaS, AI tools, mobile/web apps, agent-style products, dev tools, productivity tools — anything where the screen IS the product. Viewers convert when they see live UI doing the thing in <5 seconds; the close-up beat is the demo, the bookends are the social proof. Not pure hardware (→ TECH_UNBOX).
• Sensory anchors: micro-thumb gesture, brand-color highlight, UI alive with small motion, ambient room tone.
• Setting: cozy bedroom or couch POV; jeans/joggers at frame edges; warm window light.
• Close-up beat device: laptop on bed (desktop screenshot) or phone in hand (mobile screenshot — set

  mobile=true

  in step 3).
• Dialogue character: hook is bewildered curiosity — the creator can't categorize the thing yet, that's the point. Do NOT use feature lists or marketing language in the hook; lean into "I don't know what to call this" / "this is wild" register that makes the viewer wait for the name. Arc: bewildered hook → name the product + interaction model in human terms ("you just talk to it", "it builds X from Y") → reveal what it produces (concrete comma-separated examples) while close-up shows the page → personal-insight twist (what it replaces / changes in the user's workflow) → punchline + implicit/explicit "go try it" CTA.

• When to use & why: food brands, drinks, kitchen tools, snacks, restaurants with a takeout product — anything where the sensory peak (pour / sizzle / steam / first bite) carries the value prop. Viewers convert on hunger response — show the sensory peak, don't describe it.
• Sensory anchors: packaging rustle, knife-on-board, sizzle, pour stream, steam rising, satisfied exhale on the first bite.
• Setting: marble counter or warm wood kitchen, top-down framing.
• Close-up beat device: a product/dish close-up rather than a screen; phone in hand on the counter only if the brand has a delivery/recipe app.
• Dialogue character: hook is show-don't-tell — frame as a demonstration the viewer is watching unfold, not a description. The hook line lands while a hand or first ingredient is already in motion; the visual carries the curiosity. Arc: demonstration hook → name the product + first impression → narrate the sensory peak as it happens (pour / sizzle / steam) → satisfaction insight ("this is the new default") → punchline that hands off the recipe or shop link.

• When to use & why: skincare, makeup, cosmetics, fragrance, hair products, body care — anything where before/after + application ritual is the value prop. Viewers convert on visual transformation under matched lighting; symmetry between hook and outro is what sells the result as real. Not packaging-heavy luxury (→ HAUL_UNBOX).
• Sensory anchors: pump press, squeeze, glide on skin, glow lift, droplet beading, brush sweep.
• Setting: bathroom mirror, natural daylight or vanity lighting; same angle for the hook and the outro.
• Close-up beat device: a product close-up (bottle / tube / compact held in hand), not a screen.
• Dialogue character: hook is time-stamped social proof — name the duration ("X days in", "morning of week 3", "after one tube") to signal real use rather than paid promo. The hook plants the symmetry payoff that arrives in the after-shot. Arc: timed-claim hook → name + key ingredient or claim → narrate the application as it happens (close-up of fingers/brush on skin) → after-shot reveal (same angle as hook) → punchline that signals exclusivity or repurchase intent.

• When to use & why: workout equipment, supplements, recovery tools, activewear, fitness apps with tracking — anything where the work-to-result transformation is the value prop. Viewers convert on relatable struggle followed by earned payoff — showing the protein-shake bottle is not enough, you have to show the workout.
• Sensory anchors: heavy breathing, scoop hitting powder, equipment click, sweat catching light, post-workout exhale.
• Setting: gym or home-gym; workout gear at frame edges; floor or bench level.
• Close-up beat device: phone in hand showing app stats / heart rate / time elapsed, OR product packaging close-up (scoop in jar, bottle pour).
• Dialogue character: hook is relatable resistance — name the struggle / friction / not-wanting-to ("I did NOT want to do this", "almost skipped today", "this was supposed to be a rest day"); earns trust by sharing the tired feeling before showing the work. Arc: resistance hook → name the product + protocol ("I'm on day X of Y") → narrate mid-work moment while close-up shows the device or scoop → satisfaction insight that earns trust → punchline that frames continued use.

• When to use & why: gadgets, hardware, electronics, smart-home devices, wearables, peripherals, AI hardware (Framework laptop, AirPods, Whoop, Rabbit r1, Friend pendant, mechanical keyboards, ergonomic gear) — anything where the device + first-use moment is the value prop. The box ceremony signals premium positioning; viewers convert on seeing "does it actually work / what does it do" — the first-use beat is the conversion moment. Not HAUL (→ HAUL_UNBOX), not pure software/SaaS (→ APP_REVEAL).
• Sensory anchors: utility-knife slice, plastic peel, foam slide-out, power-on chime, tactile button press, haptic click, fan spin-up.
• Setting: wood desk, top-down framing during unbox; handheld during first-use; desk/lap context for ongoing use.
• Close-up beat device: the device itself once unboxed and powered on.

  @Image2

  is typically a real photo of the device's screen at its key UI moment (first measurement, paired status, hero feature open); if the device has no screen, a clean hero photo of it mid-use.
• Dialogue character: hook is arrival ceremony — name that this is happening now ("just got this", "opening it"). Anticipation > description; the hook plants the question "what does it do?" that the first-use beat answers. Do NOT lead with specs. Arc: arrival hook → name + one-line spec headline → first-use reveal while close-up is on the device doing its thing → workflow-change insight ("this replaces / changes / fixes my X") → punchline that hands off urgency (price, where to find, time-limited).

identity_voice_sample_url

null

• If non-null → capture as

  voice_sample_url

  and pass it on the next call's

  reference_audio

  array. Both seedance and kling accept

  reference_audio

  (seedance up to 3, ≤15s combined; kling up to 8). The model uses the sample to clone the speaker's timbre for the lip-sync.
• If null → skip; the model uses its default voice.

generate_reference_video

• provider

  :

  seedance

  (default) or

  kling

  if user passed

  provider=kling

• aspect_ratio

  :

  9:16

  (default);

  3:4

  allowed only on seedance

• resolution

  :

  720p

  (seedance only)

• duration

  : 15

• reference_images

  :

  [avatar_url, screenshot_url]

  (drop

  screenshot_url

  if step 3 failed)

• reference_audio

  :

  [voice_sample_url]

  (omit the param entirely if step 6 returned null)

• prompt

  : the multi-beat string from step 4

• sound

  : true (default — ambient + lip-sync produced by the model)

provider=kling

shots: [{prompt, duration}, ...]

prompt

<<<image_1>>>

<<<image_2>>>

@Image1

@Image2

{ task_id, status: "queued" }

task_status(task_id)

completed | failed | cancelled

completed

result.url

video_url

422 content_policy_violation

image_urls

reference_images

generate_image

• provider: "seedream"

  (native Pixar/3D-animated look)

• reference_images: [avatar_url]

  (the new plural form;

  reference_image: <url>

  is still accepted as a deprecated single-image alias for back-compat — see [pika-mcp-server BACK-339, 2026-05-10])

• aspect_ratio

  : same as the ad's aspect ratio

• resolution: "1K"

• watermark: false

  (seedream-only knob added by BACK-339 — keep the restyled avatar clean of provider watermark for the downstream lip-sync re-render)

• prompt: "Stylized 3D game character render — Unreal Engine 5 / Overwatch / Valorant / Apex Legends visual style. Anatomically grounded facial proportions with subtle stylization: slightly larger expressive eyes, defined sculpted cheekbone planes, smooth skin shader (smoother than photoreal, no micropore detail), idealized but believable features. PBR materials with subtle subsurface scattering, strand-based hair simulation, crisp cloth shader. Cinematic three-point studio lighting with strong rim light. Clearly a stylized AAA-game-character render — NOT photorealistic person, NOT Pixar plastic-toy cartoon, NOT exaggerated big-head proportions. Same person, same glasses, same outfit, same accessories. Centered medium portrait, neutral indoor background."

avatar_url_cartoon

generate_reference_video

reference_images: [avatar_url_cartoon, screenshot_url]

[avatar_url_cartoon]

result.url

video_url

content_policy_violation

provider=kling

captions=false

add_captions

edit_text_overlay

add_captions

• video_url

  :

  video_url

  from step 7

• style

  :

  "tiktok"

  (default — word-by-word purple highlight, Bebas Neue, all caps, rendered at the bottom of the frame; classic TikTok-creator look that keeps the face and screen clear). Alternatives:

  "hormozi"

  (lower-middle yellow highlight, more aggressive — overlays part of the phone-in-hand close-up beat),

  "classic"

  (plain bottom subtitle bar, safest),

  "karaoke"

  (progressive color fill, also bottom).

• font_size

  :

  60

  — overrides the per-style default; tuned for 9:16 readability without dominating the frame.

• language

  : pass the BCP-47 code for the page language detected in step 1 (

  "en"

  ,

  "zh"

  ,

  "ja"

  ,

  "es"

  , etc.) — skips auto-detect and avoids misrouting CJK to a Latin-only font path.

final_url

• /pika:ugc-ads https://pika.me avatar_url=https://cdn/face.png

  → APP_REVEAL, 9:16, seedance, real screenshot, captions on

• /pika:ugc-ads https://maisonbrune.com avatar_url=https://cdn/face.png aspect_ratio=3:4

  → HAUL_UNBOX, 3:4, seedance

• /pika:ugc-ads https://pika.me avatar_url=https://cdn/face.png provider=kling captions=false

  → APP_REVEAL, 9:16, kling shots[], no captions

• /pika:ugc-ads https://pika.me

  → no

  avatar_url

  → uses the built-in fallback Pixar-style female creator portrait, runs end-to-end