Prompt SegB

A 13-second vertical 9:16 educational short, an East Asian knowledge-worker character sharing a productivity method. Segment B of a 2-segment 25s video. 4 shots, documentary realism style (NOT AI-art aesthetic, NOT 3D render, NOT illustration). Conversational quick pace, slightly faster than typical narration (about 1.1x speed feel). This must visually match Segment A perfectly — same character, same voice, same setting.

[Character Lock]
The character is an East Asian person in their late 20s to early 30s, focused expression, casual professional appearance. Wearing a dark cotton long-sleeve button-up shirt, no jacket, with a small black lavalier microphone clipped at the collar. Hair tied back or short and neat. Same outfit and appearance across all 4 shots. Must visually match Segment A character exactly. Natural skin texture with visible pores, NOT smooth plastic, NOT over-smoothed. Real photograph quality.

[Setting Lock]
Modern home office. Wooden desk with a silver monitor visible in soft focus on the left side. Wooden bookshelf with books in the background. Large window on the right with diffused natural daylight. Apple keyboard and notebook on desk surface. Warm wood-toned aesthetic. Same room as Segment A.

[Voice Lock]
English language with neutral accent, voice age 28-32, energetic but composed, authoritative-yet-warm tone. Same voice as Segment A. Short sentences, no trailing pauses. Conversational quick pace.

[Camera Grammar]
Medium static 50%, slight orbit 25%, low-angle CTA push-in 25%. Cuts seamless, no whip pan blur. Each cut triggered by transition to a new step.

Shot 1 (0 to 4 seconds) — Step #1: The character mid-explanation gesture with right hand (palm slightly outward, presenting). Soft abstract glowing rectangular shapes hovering near the right edge of the frame (teal/soft-blue/warm-white gradient hues, NO text, NO Chinese characters, NO English text, NO numbers, NO logos, occupying about 25% of the right side). Camera medium static, eye-level, straight on. Voiceover in instructive tone: "Step one: frame the problem in one sentence." Mouth movement strictly synchronized.

Shot 2 (4 to 8 seconds) — Step #2: Cut to character with both hands gesturing outward in a presenting motion. The right-edge color shapes from Shot 1 expand and multiply outward into floating cards around the character. Camera slowly orbits 15 degrees to the character's right side. Voiceover in instructive tone: "Step two: draft fast, edit slow." Mouth movement strictly synchronized.

Shot 3 (8 to 11 seconds) — Step #3: Cut to character surrounded by exactly 8 floating rectangular cards (teal/soft-blue/warm-white gradient with subtle rainbow tones) arranged in a partial ring around them — some cards in front, some behind, some on the sides. Camera slight high angle (10-15 degrees from above), wider medium shot. Voiceover in confident climactic tone: "Step three: one final polish pass." Mouth movement strictly synchronized.

Shot 4 (11 to 13 seconds) — CTA: Cut to character with composed expression, slight affirming nod, small inviting smile (lips just parted, friendly), eyes directly at camera. Camera low angle (10 degrees from below), tighter medium close-up. The floating cards from Shot 3 are gone, returning to a clean home office background. Voiceover in warm authoritative tone: "DM 'method' — I'll send the full template." Mouth movement strictly synchronized. Final 0.3 second hold on warm smile.

[Quality directives]
The character's facial features remain consistent across all 4 shots and must match Segment A exactly — same face, same hair, same dark cotton shirt, same black lavalier mic at collar. Floating cards must be abstract gradients only — NO text, NO Chinese characters, NO English text, NO numbers, NO logos, NO UI elements, NO recognizable symbols. Hands have natural anatomy with five fingers and correct proportions. Skin shows natural texture with pores and subtle imperfections. Eyes remain stable without flickering. Mouth movement strictly synchronizes to assigned dialogue per shot — closed and still otherwise. Lip-sync precise to each English syllable. Lighting consistent with natural daylight from the window throughout. Documentary realism throughout, NOT AI-art aesthetic, NOT 3D render, NOT illustration.