---
name: lyric-engine
description: Generate lyric music videos from audio + footage. Uses Whisper STT to align lyrics word-by-word to the audio, then ffmpeg renders animated typography (one word at a time, beat-aware crash zooms) over your video footage. Use when the user wants a lyric video, word-aligned typography, kanye-style lyric drops, or to make a song's words appear synced to the audio.
---


# lyric-engine

Lyric music video pipeline: audio → Whisper word timestamps → ffmpeg type animation over footage.

## Run

```bash
python3 ~/.claude/skills/lyric-engine/scripts/lyric_engine.py \
  --audio track.mp3 \
  --video footage.mp4 \
  --out lyrics.mp4 \
  --style impact
```

If you already have lyrics with timestamps (`.srt`/`.json`):

```bash
python3 ~/.claude/skills/lyric-engine/scripts/lyric_engine.py \
  --audio track.mp3 \
  --video footage.mp4 \
  --srt lyrics.srt \
  --out lyrics.mp4
```

## Styles

- `impact` — huge condensed centered, white on black, classic
- `flash` — single word at a time, jump cuts on each
- `wall` — repeated background tapestry of the active word (blodheaven inspired)
- `sub` — small bottom-third subtitle, music-video staple

## Notes

- First run pip-installs `openai-whisper` (~1GB with PyTorch).
- Use `--model tiny` for fast iteration, `--model small` for production.
- Footage gets auto-scaled and looped to match audio duration.