About Cadence

Cadence is an AI‑driven speech‑to‑marker tool for After Effects built around WhisperX. Point it at an audio layer and it places a frame‑accurate marker on every spoken word automatically. Word‑level forced alignment and Wav2Vec2 provide millisecond‑precise word boundaries and phoneme‑level accuracy, supporting 90+ languages. Markers are added to the audio layer, keeping the composition clean, and can be copied to the current timeline, parent layer, or parent timeline with a single click. The plugin processes multiple audio layers in one operation and maintains zero drift even for hour‑long audio. It is compatible with After Effects CC 2018 through 2026 on both Windows 10/11 and macOS.

Features

• Word-level forced alignment places each marker at the exact millisecond a word begins, with Wav2Vec2 detecting word boundaries at phoneme-level precision
• Smart labeling shows the spoken word on each marker, turning the timeline into a readable script
• Multi-layer processing handles several selected audio layers in a single operation
• Marker sync copies markers to the current timeline, parent layer, or parent timeline with one click
• Non-destructive: markers sit on the audio layer, keeping the comp clean and organized
• 90+ languages, including English, French, Spanish, German, and Japanese
• Zero drift keeps sync accurate from the first word to the last, even on hour-long audio

Best for

Kinetic typography, lip‑sync animation, audio‑reactive motion, keyword highlighting, diagram reveals, and infographic timing synced to a voiceover.