ugc

UGC means it must look like a real person filmed it, not a brand. Imperfection beats polish. Hand-held framing, single light, casual room — these are the visual cues that buy trust on Meta / TikTok feeds.

Phase 1 — Persona + script

1. Activate skill(video-hooks), skill(video-spec-sheet), skill(ad-frameworks).
2. Define the persona: name, age range, tone, accent, look. UGC needs ONE recognizable creator, not multiple.
3. Pick the avatar:
   • Photoreal, off-the-shelf → HeyGen public avatar.
   • Photoreal, brand-specific → HeyGen Avatar IV from a single photo (founder / employee / paid model release).
   • Stylized / illustrated / non-human → Hedra Character-3.
4. Pick the voice:
   • Off-the-shelf → ElevenLabs voice ID.
   • Cloned founder/employee → ElevenLabs Voice Clone (consent on file).
   • Localized → ElevenLabs multilingual model (or HeyGen Translate post-render).
5. Write the script (HSO for cold, PAS for problem-aware). 3 hook variants, body shared. Save to ./video-out/<slug>/script.md.
6. Storyboard, marking: avatar shots (talking head), cutaway shots (product, b-roll, screen-cap), on-screen text cards.

Phase 2 — Avatar renders

For each hook variant + body combination:

1. Generate avatar video via avatar capability (HeyGen heygen_create_video with avatar_id + voice_id + script).
2. Save to ./video-out/<slug>/avatar/<variant>-body.mp4.
3. If using Avatar IV: pre-create the avatar from a reference photo before the first render.

Phase 3 — B-roll cutaways

Cutaways punch up retention in talking-head UGC. ~30–40% of total runtime should be cutaways.

1. Product shots — image-gen at the product's actual look (Flux primary, gpt-image-1 for typography).
2. Lifestyle b-roll — Pexels stock first (free); generate via video-gen only when stock can't deliver (Hailuo cheap-first).
3. Screen-cap — if the product is software, the user records once; you stitch.

Save cutaways to ./video-out/<slug>/cutaways/.

Phase 4 — Lipsync polish (optional)

If the avatar's lipsync looks soft (HeyGen sometimes drifts on consonant-heavy lines), run the cut through lipsync (Sync.so) to tighten.

This is per-second pricing — only run on the finished, picked variant, never on rejects.

Phase 5 — Voice + audio bed

1. Pre-render voiceover in voice (ElevenLabs) per beat — used for any non-avatar narration over cutaways.
2. Generate or pick a low-key bed track via music (Mubert). UGC ads typically run muted music or no music — don't fight the voice.
3. Sound design: minimal. UGC reads as authentic when it sounds like a phone-recorded clip, not a produced commercial.

Phase 6 — Captions

1. Burn captions on the final cut (sound-off is the default on Meta + TikTok).
2. Word-by-word reveal in time with VO. Use captions (AssemblyAI for word-level timestamps).
3. Caption style: bold sans, 80–110pt, center-upper-third, white with black stroke.

Phase 7 — Stitch + variant scaling

1. Compose: avatar + cutaways + captions + audio bed.
2. Default stitcher: composition with ffmpeg. Use Remotion when generating ≥10 templated variants from the same hook + body skeleton.
3. Variant scaling rule: ship 3–5 hook variants of the SAME body. Same avatar, same body, different first 1.5s. This is how UGC ads survive ad-fatigue.

Phase 8 — Bundle for ads platforms

./video-out/<slug>/
  ads/
    variant-A-9x16.mp4
    variant-B-9x16.mp4
    variant-C-9x16.mp4
    variant-A-1x1.mp4   (FB feed cut)
    variant-A-4x5.mp4   (IG feed cut)
  meta/
    primary-text.md     (per variant; 125 chars max for IG primary text)
    headlines.md        (40 chars max)
    descriptions.md     (30 chars max)
    landing-utms.md     (UTM-tagged URLs per variant)
  ads-library-checklist.md

Skills

Memory protocol

Before starting:

• remember(["persona", "avatar id", "voice id", "winning hooks", "banned claims", "consent on file"])

After completing:

• memorize() — persona that worked, hook patterns by vertical, lipsync polish needed (yes/no), avatar/voice combo wins.

• Avatar in frame ≥40% of runtime. Cutaway-heavy UGC tests as "branded content" by both Meta and TikTok algorithms.
• First 1.5s must be the avatar speaking the hook, not a logo, not a stock cutaway.
• Single creator across all variants in a campaign. Mixing creators reads as branded.
• No music duck on the avatar's voice. Music should be -18 dB or off.
• Captions stay in the upper-center third (avoid Meta's lower CTA bar).
• Length: 15–25s tests best on Meta, 25–40s on TikTok. Don't go above 60s for paid UGC.
• Hook variants ≥3. Test in Meta Ads Manager with one ad set per hook.

Do:

• Avatar in frame ≥40% of runtime.
• 3+ hook variants per campaign.
• Captions burned in.
• Consent confirmation step before any Avatar IV creation.
• remember() before, memorize() after.