Skip to content
Agentmart
Submit a tool

normalize-format

Convert audio to a transcription-friendly format — stereo to mono, resample to 16kHz, compress WAV to opus or mp3, reduce bitrate.

Skill by danielrosehill

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/danielrosehill-normalize-format

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Convert audio to a transcription-friendly format — stereo to mono, resample to 16kHz, compress WAV to opus or mp3, reduce bitrate. Use when the user asks to normalize audio format, downmix, resample, compress, or prepare audio for transcription.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/normalize-format

What's inside

Skill name
normalize-format
Description
Convert audio to a transcription-friendly format — stereo to mono, resample to 16kHz, compress WAV to opus or mp3, reduce bitrate. Use when the user asks to normalize audio format, downmix, resample, compress, or prepare audio for transcription.
License
MIT
Instructions
33 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Normalize audio format

Standardize audio for transcription pipelines. Transcription engines generally work best at 16kHz mono, and compressed formats (opus) are faster to upload without quality loss for speech.

## Default transform

```bash
ffmpeg -i INPUT -ac 1 -ar 16000 -c:a libopus -b:a 24k OUTPUT.opus
```

- `-ac 1` → mono
- `-ar 16000` → 16 kHz sample rate
- `libopus @ 24k` → excellent speech quality at ~11 MB/hr

## Variants

- **Whisper-native WAV**: `-ac 1 -ar 16000 -c:a pcm_s16le OUTPUT.wav`
- **MP3 (compatibility)**: `-ac 1 -ar 16000 -c:a libmp3lame -b:a 32k OUTPUT.mp3`
- **Preserve sample rate**: omit `-ar`

## Output convention

`<source_stem>.normalized.<ext>`

## Parameters

User may specify:
- target format (`opus`/`mp3`/`wav`)
- bitrate
- keep stereo (`--stereo`)
- preserve sample rate (`--keep-sr`)

From danielrosehill/Claude-Transcription-Plugin, MIT.

More from danielrosehill/Claude-Transcription-Plugin

Signals

Stars
1
Forks
2
Open issues
0
Last commit (this folder)
Apr 19, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from danielrosehill

Cite this page

normalize-format skill. Agent Mart. https://agentmart.dev/skills/danielrosehill-normalize-format (last updated 2026-10-24)