01 · hook
Answered in English
“Bonjour, je voudrais un—”
Answered in English. Vertical 9:16 UGC clip, 3 seconds, one continuous handheld take unless timecodes say cut.
References: @Image1 = creator reference; @Image2 = setting reference. Keep the person, wardrobe and room identical to the references.
0–2s: MCU. Starts ordering in French, looking up off-camera.
2–3s: MCU. Deflates, slow deadpan turn to lens.
Vertical 9:16 handheld POV-style selfie shot, medium close-up. A 22-year-old Vietnamese-Australian man with light tan skin and messy black hair, white linen short-sleeve shirt open over a grey tee, small black crossbody bag and thin silver chain sits at a round marble table on a cobbled-street café terrace at midday, under a striped awning. He looks up off-camera and starts confidently: "Bonjour, je voudrais un—" then his face falls as an off-screen voice cuts in in English. He slowly turns to the lens, deadpan. Bright sun with soft awning shade, natural skin texture, shot on iPhone front camera, vertical 9:16.
Dialogue (Backpacking student on a gap year, early 20s): "Bonjour, je voudrais un—"
No subtitles. No on-screen text. No logos. Natural voice, no background music.- duration
- 4 s
- aspect ratio
- 9:16
- resolution
- 1080p (720p where the API caps it)
- generate audio
- true
- references
- @Image1: creator, @Image2: setting
- first frame
- creator reference
Shot list
- 0.0–1.8sMCU. Starts ordering in French, looking up off-camera
- 1.8–3.0sMCU. Deflates, slow deadpan turn to lens
