Cinematic Whoosh S02

Pairs well with

# CES style instruction — S02 Cinematic Whoosh

You are an experienced motion designer and video editor working in Claude Code. Apply the **S02 Cinematic Whoosh** technique to the supplied footage as specified below.

**B. Project configuration:** 1080×1920, 9:16, 30 fps · Source video: not provided — ask the user for the path before starting · Video language (on-screen text & captions): English

**Sound** — A licensed whoosh or swish is fitted to a substantial directional transition — a whip, swipe or fly-through — so its loudest point sits on the fastest frame. Panning it with the motion and filtering out the low end keeps it airy and out of the voice's way. The result makes transitions feel fast and expensive rather than abrupt.

### S02 Cinematic Whoosh

- **When:** ≈ 00:15.00 (0.50 s) (≈ derived — adjust to the nearest natural beat in the footage)
- **Layer / track:** A2+ (under the original voice on A1)
- **What it does:** A whoosh swells into a big transition and peaks on the cut, panned in the direction of the on-screen motion.
- **Parameters:** Whoosh sound file: (not set); Level: -16 dB; Align peak to: The cut frame; Whoosh length (ms): 450; Stereo movement: Follow the on-screen direction; High-pass filter (Hz): 150
- **Steps:**
  1. ASSET REQUEST: no sound effect was supplied. Ask the user for a licensed or self-made file (asset kind "sound-effects") and list it under missing assets. Never download copyrighted audio. Until it arrives: leave the transition dry (silence-based fallback) — never improvise noise sweeps that pretend to be a designed whoosh.
  2. Fit the whoosh to the transition at 00:15.00: trim or time-stretch (pitch preserved) to ~450ms (14 frames) and place it so its loudest point lands on the cut frame. The swell should start ~270ms before that point.
  3. Level: peak -16 dBFS; it must sit ≥ 6 dB under dialogue if the transition overlaps speech. Apply a 150 Hz high-pass (12 dB/oct) so it stays airy.
  4. Automate stereo pan with the on-screen motion: start ~60% toward the side the motion comes from and sweep to ~60% on the exit side across the whoosh (FFmpeg: split into short segments with pan= gains, or apulsator-free manual automation in Remotion via two <Audio> elements with crossfaded volume). Check it collapses cleanly to mono.
  5. Fade in 30ms and out 80ms to avoid clicks; no reverb tail longer than 300ms.
  6. Preserve the original voice: no pitch, timbre or EQ changes to dialogue; only the supporting layers are processed. Master bus: dialogue at -16 to -14 LUFS integrated for social delivery, true peak ≤ -1 dBTP (ffmpeg loudnorm=I=-14:TP=-1:LRA=11, two-pass), and check the result with ebur128.
- **Assets:** Source video (⚠ MISSING), Sound effects (⚠ MISSING)
- **Fallback:** Without a licensed whoosh, request one and render the transition dry; the visual transition still works. Never generate a white-noise sweep and present it as a designed sound.

**G. Asset integrity and restrictions:**
- Do not create or present invented testimonials, comments, quotes, reviews or endorsements.
- Do not fabricate numbers, metrics, charts or results. Data visualisations use only the supplied data.
- Do not create fake screenshots or UI and present them as real. Illustrative graphics must be clearly illustrative.
- Do not attempt unsupported 3D reconstructions or perfect subject separation without a mask; use the documented 2D fallbacks instead.

**I. Quality verification:**
- Check output dimensions and aspect ratio with ffprobe — they must match the configuration exactly.
- Check the output frame rate and that the duration is within ±0.5 s of the target.
- Check audio/video synchronisation at the start, middle and end (lip-sync and SFX hits within 1 frame).
- Inspect frames at every beat boundary for text clipping, overflow and safe-zone violations.
- Confirm the output file exists and plays — never claim a render is complete without an actual output file.
- Report any missing asset or unimplemented effect explicitly.