Add a music bed

What it asks you for

Voiceover or videorequired

What the music goes under.

Music mood

The feel you want.

What it tells the AI to do

The full instructions, exactly as they run.

Put a music bed under {{ media }}.

Mood: {{ mood }}

The music must DUCK under the voice, not merely sit quieter. Use a sidechain
compressor so it drops when someone speaks and comes back when they stop:

```bash
ffmpeg -i /tmp/input/voice.wav -i /tmp/input/music.mp3 -filter_complex \
  "[1:a]volume=0.35[m];[m][0:a]sidechaincompress=threshold=0.05:ratio=8:attack=20:release=400[duck];[duck][0:a]amix=inputs=2:duration=first" \
  /tmp/output/mixed.wav
```

Fade the music in over ~1s and out over ~2s. Only use music the user has rights
to — do not pull a track from a streaming service or a random URL.
## Delivery

Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.

• audio
• music
• mix

More audio skills

• Read this aloudTurn text into natural speech with a chosen voice.
• Transcribe and summarizeTurn audio or video into a transcript plus a summary with action items.