Skip to main content
Agent skill

Audio Split

Splits a single audio file into two segments (part 1 before the split point, part 2 after) using FFmpeg. Use when the user wants to split audio, divide a clip into two parts, cut at a timestamp, or separate intro from body.

Get started

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

When to use this skill

Use Audio Split when an AI agent needs a reusable SKILL.md workflow for this job: Splits a single audio file into two segments (part 1 before the split point, part 2 after) using FFmpeg. Use when the user wants to split audio, divide a clip into two parts, cut at a timestamp, or separate intro from body.

When not to use it

Skip Audio Split 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-split
# Save SKILL.md to ~/.claude/skills/audio-split/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/audio-split/SKILL.md. For a shared project, commit the folder at .claude/skills/audio-split/ 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 Split skill for this task: Use Audio Split 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 Split

Split one audio file into **part 1** (start → split point) and **part 2** (split point → end).

## 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: split at **50%** of duration, output to `<audio-dir>/audio-split/`:

```bash .dependency/python/python .ai/audio-split/split.py --audio path/to/audio.wav ```

Split at a specific time (seconds):

```bash .dependency/python/python .ai/audio-split/split.py --audio path/to/audio.wav -s 1.25 ```

Outputs: `basename_part1.ext` and `basename_part2.ext`.

## Split Point

Provide **one** of:

| Flag | Meaning | |------|---------| | `-s` / `--split-at` | Time in seconds (e.g. `1.25`, `90`) | | `-p` / `--percent` | Position as percent of duration (e.g. `50` = midpoint) | | *(none)* | Defaults to **50%** |

If both `-s` and `-p` are given, `-s` wins.

## Common Flags

`--audio` · `-s` / `--split-at` · `-p` / `--percent` · `-o` / `--output`

```bash .dependency/python/python .ai/audio-split/split.py --audio audio/sfx.wav -s 0.4 .dependency/python/python .ai/audio-split/split.py --audio audio/sfx.wav --output path/to/out/ ```

Originals are never modified. Supported: `.wav`, `.mp3`, `.ogg`, `.flac`, `.aac`, `.m4a`, `.wma`.

## Agent Notes

1. Use the bundled script, not hand-written `-ss`/`-to` commands. 2. **Looping BGM** — splitting breaks the loop; prefer two source assets or manual crossfade planning. 3. Split point at `0` or at/after duration → script errors with a clear message. 4. Missing Python/FFmpeg → populate `.dependency/` per skill-dependency-manager, retry same command. 5. FFmpeg details and manual fallback: [reference.md](reference.md)

## Tests

From repo root:

```bash .dependency/python/python .ai/audio-split/test_split.py ```

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

Intended uses

  • Use Audio Split 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.