Skip to main content
Agent skill

Audio Denoise

Reduces background noise in a single audio file using FFmpeg afftdn. Use when the user wants audio denoise, noise reduction, hiss removal, room noise cleanup, or SFX/voice cleanup before normalization.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Audio Denoise when an AI agent needs a reusable SKILL.md workflow for this job: Reduces background noise in a single audio file using FFmpeg afftdn. Use when the user wants audio denoise, noise reduction, hiss removal, room noise cleanup, or SFX/voice cleanup before normalization.

When not to use it

Skip Audio Denoise when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/audio-denoise
# Save SKILL.md to ~/.claude/skills/audio-denoise/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/audio-denoise/SKILL.md. For a shared project, commit the folder at .claude/skills/audio-denoise/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Audio Denoise skill for this task: Use Audio Denoise when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

70/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
61/100
Source signals
72/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Audio Denoise

Reduce background noise via FFmpeg `afftdn`.

## Rules

When this skill applies, read and follow [skill-dependency-manager](../skill-dependency-manager.md) — run scripts as documented, install missing tools into `.dependency/`.

## Quick Start

Denoise a single audio file, output to `<audio-dir>/audio-denoise/<audio-name>`:

```bash .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`

```bash .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

1. Use the bundled script, not hand-written `afftdn` filters. 2. **Default is light denoise** — do not raise `--nr` unless the user asks; heavy denoise dulls transients. 3. Missing Python/FFmpeg → populate `.dependency/` per skill-dependency-manager, retry same command. 4. **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:

```bash .dependency/python/python .ai/audio-denoise/test_denoise.py ```

Manual CLI examples: [cli/audio-denoise.md](../../../cli/audio-denoise.md)

Intended uses

  • Use Audio Denoise when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.