Audio Fade
Applies fade-in and fade-out at the start and end of a single audio file using FFmpeg. Use when the user wants audio fade, fade in/out, smooth attack/release, crossfade prep, SFX envelope shaping, or mentions afade.
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Audio Fade when an AI agent needs a reusable SKILL.md workflow for this job: Applies fade-in and fade-out at the start and end of a single audio file using FFmpeg. Use when the user wants audio fade, fade in/out, smooth attack/release, crossfade prep, SFX envelope shaping, or mentions afade.
When not to use it
Skip Audio Fade 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?
mkdir -p ~/.claude/skills/audio-fade # Save SKILL.md to ~/.claude/skills/audio-fade/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/audio-fade/SKILL.md. For a shared project, commit the folder at .claude/skills/audio-fade/ instead.
- 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.
- 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.
Use the Audio Fade skill for this task: Use Audio Fade 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 Fade
Apply **fade-in** at the start and **fade-out** at the end without changing clip length.
## 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
Default: **1 s** fade-in and fade-out, output to `<audio-dir>/audio-fade/<audio-name>`:
```bash .dependency/python/python .ai/audio-fade/fade.py --audio path/to/audio.wav ```
Fade-in only (keep full end level):
```bash .dependency/python/python .ai/audio-fade/fade.py --audio path/to/audio.wav --no-fade-out ```
Custom durations (seconds):
```bash .dependency/python/python .ai/audio-fade/fade.py --audio audio/sfx.wav -fi 0.05 -fo 0.15 ```
## Duration Guidelines
| Asset | Fade-in | Fade-out | |-------|---------|----------| | UI clicks / ticks | 0.01–0.05 s | 0.02–0.08 s | | Impacts / weapons | 0.02–0.08 s | 0.05–0.15 s | | Voice lines | 0.05–0.15 s | 0.1–0.25 s | | Ambience beds | 0.3–1.0 s | 0.5–2.0 s | | BGM one-shots | 0.2–0.5 s | 0.3–1.0 s |
Fade-in + fade-out must stay **shorter than file duration**. Very short clips need smaller values.
## Common Flags
`--audio` · `-fi` / `--fade-in` · `-fo` / `--fade-out` · `--no-fade-in` · `--no-fade-out` · `-o` / `--output`
```bash .dependency/python/python .ai/audio-fade/fade.py --audio audio/sfx.wav -fi 0.03 -fo 0.08 ```
Originals are never modified. Input must be a single audio file (`--audio`), not a directory. Supported: `.wav`, `.mp3`, `.ogg`, `.flac`, `.aac`, `.m4a`, `.wma`.
Fades use FFmpeg `afade` with the linear `tri` curve. The script probes clip duration and places fade-out at `duration - fade_out`.
## Scope
- **Fade** shapes volume at clip boundaries without changing its duration. - **Trim** removes silence or crops boundaries; use the `audio-trim` skill. - **Crossfade** overlaps two clips and is not performed by this skill.
## Agent Notes
1. Use the bundled script, not hand-written `afade` filters. 2. **Looping BGM** — avoid fade-out on loop assets; use `--no-fade-out` or fade-in only for one-shot intros. 3. Clicks with instant attack → `--no-fade-in` or lower `-fi` (e.g. `0.01`). 4. Tail cut off abruptly after fade → increase `-fo`; tail too soft → decrease `-fo`.
## CLI
Copy-paste commands: [cli/audio-fade.md](../../../cli/audio-fade.md)
Intended uses
- Use Audio Fade 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.