Audio Denoise
Reduce background noise via FFmpeg afftdn.
Rules
When this skill applies, read and follow skill-dependency-manager — run scripts as documented, install missing tools into .dependency/.
Quick Start
Denoise a single audio file, output to <audio-dir>/audio-denoise/<audio-name>:
.dependency/python/python .ai/audio-denoise/denoise.py --audio path/to/audio.wav
Defaults
| Setting | Default | Notes |
|---|---|---|
| Denoise | afftdn |
nr=10 dB, nf=-25 dB — conservative for SFX |
Common Flags
--audio · --nr · --nf · --output
.dependency/python/python .ai/audio-denoise/denoise.py --audio Audio/SFX/click.wav
.dependency/python/python .ai/audio-denoise/denoise.py --audio Audio/Voice/line.wav --nr 8
Originals are never modified. Input must be a single audio file (--audio), not a directory. Supported: .wav, .mp3, .ogg, .flac, .aac, .m4a, .wma.
Agent Notes
- Use the bundled script, not hand-written
afftdnfilters. - Default is light denoise — do not raise
--nrunless the user asks; heavy denoise dulls transients. - Missing Python/FFmpeg → populate
.dependency/per skill-dependency-manager, retry same command. - Do not copy, move, or replace the source with denoised output — tell the user where
audio-denoise/files are; they swap assets manually when ready.
Tests
From repo root:
.dependency/python/python .ai/audio-denoise/test_denoise.py
Manual CLI examples: cli/audio-denoise.md