format-spoken-drama
Animated spoken drama ad, the "accused mom, vindicated" story (Dawn recipe A) told with voiced characters and a mom narrator instead of a song, 2-4 min.
Lane: cartoon-h3 dialogue · not built yet: 0 (see below) · source: /Users/ayden/.openclaw/workspace/skills/format-spoken-drama
Spoken drama — sources
Reference ads (Foreplay, analysed 10-06 in ~/research/davidaistar/foreplay/)
- 04_drama — Koriderm Time Reverse Cream, 4:32, 9:16. Beat shape: public humiliation hook → backstory of the insult → secret discovery → transformation → the accusers see it → product as the turning point. ~95% AI, EL voices + lip-sync over generated video; tells: gibberish text, morphing product label, fused fingers on application. Keep: humiliation → vindication arc, accusers witnessing the payoff. Change: our accuser is close to her and blames her for the mornings; no lip-sync (core §3), so dialogue is staged on listeners; product never applied by hand on camera.
- 14_minimovie — Rosabella beetroot, 11:51 photoreal. Shows long-form narrative holds attention when each beat raises a stake; too long and too photoreal for our lane. Keep the "every beat raises a stake" rule.
- 10_character_arguments — Penrose, 62 s 3D debate. Two voices arguing can carry a short ad; see format-courtroom.
davidaistar method notes (analysis/diff_podcast_dialogue.md, diff_copy.md)
- "80% of realism is the script": casual, interrupted, short turns. Applied in beat 4 rules.
- One generation per speaker (native-speech route) is how he gets on-camera talk; ours is the staged route until a native-speech mode is built (core §3).
Our receipts
- Recipe A evidence: MAP.md §2A (exhibit A 2.48 ROAS, oneweek 1.81; vindication payoff $1,638 at 1.81).
- 10-01 attendance-office dialogue packs: the pace keys that passed vo_check (vo_tempo 1.08, gap_same 0.15, gap_turn 0.3, max_gap 0.22, seam_gap 0.25).
- 9-30: the spoken cartoon of "Side Effects" shipped the same night the photoreal version failed (feedback_ai_avatar_broll_lane).
starpop articles (creator's own write-ups, read 2026-10-06; ~/research/davidaistar/starpop/txt/)
- Applied:
facebook-instagram-ad-sizes-and-safe-zones + how-to-preview-a-facebook-ad-before-publishing → §10 placement gate (the article names the UI regions but gives no percentages; the 14/35/6 % Reels box is Meta's published spec, cross-checked 10-06). are-ai-generated-ads-allowed-on-meta → §11 upload hygiene (Advantage+ enhancements off, live preview day 1). meta-video-ad-metrics-hook-rate-hold-rate-ctr-cpa, how-much-budget-to-test-meta-ad-creatives → §11 read/floor lines where this format needed them.
- Read, nothing new for this format:
ai-ad-formats-guide (format ↔ job table, shot-list order, references before video: already core §4), fully-ai-generated-ads-are-here-to-stay (strategy essay), how-to-calculate-break-even-roas-for-meta-ads (proposed for core §6, not format-specific), how-to-add-correct-captions-in-any-language + how-to-fix-wrong-capcut-auto-captions (script-as-source captions = our assemble rule already; his SRT → CapCut/Premiere import maps to Remotion per core §2a).
- Not adopted: (1) "an AI actor must not voice a fictional first-person experience / fabricated testimonial" (formats guide, AI-ads article, organic-vs-paid) — conflicts with Fish's claims unlock (10-02) and our dramatized mom-narrator recipe; risk is Fish's call, recorded here only. (2) His 25-char vertical caption line cap — VideoAd chunks by its own MAX_PHRASE_CHARS 28 + two-line fit, Fish-set. (3) Organic-first discovery (
ai-organic-social-vs-paid-ads) — Dawn's message and checkout path are proven, Testing CBO is our discovery lane. (4) His model picks (Kling O3 Pro, Sora 2, P-Video) — registry roles only; untested candidates.