Callout Bubble V07

Pairs well with

# CES style instruction — V07 Callout Bubble

You are an experienced motion designer and video editor working in Claude Code. Apply the **V07 Callout Bubble** 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

**Visual Beats** — A small bubble grows from a point on a visible object — a product on the desk, a tool in hand, the speaker themselves — with its tail anchored to that point. The pointer makes the connection explicit, and the short text names or explains the object. If the object moves, the anchor tracks it, so the label always belongs to the right thing.

### V07 Callout Bubble

- **When:** ≈ 00:00.00 → 00:02.50 (≈ derived — adjust to the nearest natural beat in the footage)
- **Layer / track:** V2+ (overlay above the picture)
- **What it does:** A speech bubble or label pops out of an object in the shot with a pointer tail attached to it, explaining what it is in a few words.
- **Parameters:** Bubble text: (not set); Object to attach to: (not set); Bubble style: Speech bubble; Bubble side: Auto (empty space); Track object motion: on; Duration: 2.5 s; Bubble colour: #F4F2EB
- **Steps:**
  1. The target is not set. Attach to the object the speaker refers to at this moment; if nothing specific is visible, ask rather than attaching to an arbitrary point.
  2. Bubble text: ≤ 8 words drawn from what the speaker says about the object. Do not add specs, prices or claims that are not in the transcript.
  3. Draw a rounded speech bubble (2.5% radius) with a triangular tail in #F4F2EB with Inter semibold text ≈ 3.8% of frame width (dark text on light bubbles). Place it on the side with the most empty space of the object, never over the speaker's face.
  4. Entrance: scale from 0 at the anchor point (transform-origin = tail tip) to 1.0 over 9 frames with a back-out curve with slight overshoot (cubic-bezier(0.34, 1.56, 0.64, 1)); text fades in 2 frames later.
  5. Track the anchor point frame by frame (point tracking or manual keyframes every 4–6 frames, smoothed) so the tail stays attached if the object or camera moves.
  6. Hold ≥ 2.3s, then shrink back into the anchor over 6 frames.
- **Assets:** Source video (⚠ MISSING) · optional: Transcript with timing, Subject mask / matte
- **Fallback:** If the object moves too much to track reliably, freeze the frame briefly (M04) or place the label as a lower-third instead of attaching it.

**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.