Sound

Every cut and reveal lands on a beat of the music, and the big hits land on the first beat of a bar.

Export at -14 LUFS integrated with the true peak at or under -1.5 dBTP.

A subtle tension beat that builds, instrumental, under a data reveal.

An instrumental bed under the voice, lowered whenever she speaks.

Keep the brush on the panel audible under the shot, and record 30 seconds of the room on its own.

One list of event times drives the animation, the key presses and the sound cues.

Lay recorded room tone under every generated line, roll off the highs above 7 kHz, add light compression and a short room reverb.

Run the voice through a high-pass at 100 Hz, a downward expander, a de-esser, a 3 dB lift around 3.5 kHz, a compressor and a limiter, in that order.

Generate the final voice line first, with its delivery, then give that audio to the video model as the audio reference for the face.

Write the voice-over to fit this 15-second animation, one line per shot, about 2.2 words per second, the last two seconds left free for the end card.

The impact lands on the exact frame where the logo stops moving.

A whoosh on the zoom, an impact as the title lands, a soft tick on each counted number.

Half a second of full silence before the reveal, then the sound returns with the picture.

One sound event in the first second: a whoosh on the push-in, or an impact as the text lands.