ffmpeg-audio-processing

ffmpeg-audio-processing is a skill for Claude Code, Codex from benchflow-ai/skillsbench. It costs 21 tokens per session (1,267 once invoked), scanned A, original, Apache-2.0.

A guide to extracting and changing audio tracks with FFmpeg, a command-line media tool. It covers format conversion, volume changes, loudness normalization, mixing, and channel selection.

In plain words
What is it for?
Use it to extract sound from videos, normalize loudness, mix tracks, select channels, adjust volume, and export audio files.
Why use it?
It helps fix inconsistent audio levels or separate and combine tracks without needing a full audio editor.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract sound from videos, normalize loudness, mix tracks, select channels, adjust volume, and export audio files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benchflow-ai/skillsbench/ffmpeg-audio-processing
About the project

SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.

benchflow-ai/skillsbench · 1,764 stars · on GitHub · skillsbench.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add benchflow-ai/skillsbench --skill ffmpeg-audio-processing
Clone the repo
git clone --depth 1 https://github.com/benchflow-ai/skillsbench

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ffmpeg-audio-processing

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-audio-processing/github.svg)](https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-audio-processing)
Your own site
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-audio-processing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-audio-processing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ffmpeg-audio-processing

Your own site · 80×15
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-audio-processing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-audio-processing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.01267
Opus 5 $0.00010 $0.00633
Sonnet 5 $0.00004 $0.00253
Haiku 4.5 $0.00002 $0.00127

Measured 8d ago against content hash 001943d16329, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ffmpeg-audio-processing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

tasks/multilingual-video-dubbing/environment/skills/ffmpeg-audio-processing/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FFmpeg Audio Processing Skill

Extract, normalize, mix, and process audio tracks from video files.

When to Use

  • Extract audio from video
  • Normalize audio levels
  • Mix multiple audio tracks
  • Convert audio formats
  • Extract specific channels
  • Adjust audio volume

Extract Audio

# Extract as MP3
ffmpeg -i video.mp4 -vn -acodec libmp3lame -q:a 2 audio.mp3

# Extract as AAC (copy, no re-encode)
ffmpeg -i video.mp4 -vn -c:a copy audio.aac

# Extract as WAV (uncompressed)
ffmpeg -i video.mp4 -vn -acodec pcm_s16le audio.wav

# Extract specific audio stream
ffmpeg -i video.mp4 -map 0:a:1 -c:a copy audio2.aac

Normalize Audio

# Normalize loudness (ITU-R BS.1770-4)
ffmpeg -i input.mp4 -af "loudnorm=I=-23:TP=-1.5:LRA=11" output.mp4

# Simple normalization
ffmpeg -i input.mp4 -af "volume=2.0" output.mp4

# Peak normalization
ffmpeg -i input.mp4 -af "volumedetect" -f null -
# Then use the detected peak to normalize
ffmpeg -i input.mp4 -af "volume=0.5" output.mp4

Volume Adjustment

# Increase volume by 6dB
ffmpeg -i input.mp4 -af "volume=6dB" output.mp4

# Decrease volume by 3dB
ffmpeg -i input.mp4 -af "volume=-3dB" output.mp4

# Set absolute volume
ffmpeg -i input.mp4 -af "volume=0.5" output.mp4

Channel Operations

# Extract left channel
ffmpeg -i stereo.mp3 -map_channel 0.0.0 left.mp3

# Extract right channel
ffmpeg -i stereo.mp3 -map_channel 0.0.1 right.mp3

# Convert stereo to mono
ffmpeg -i stereo.mp3 -ac 1 mono.mp3

# Convert mono to stereo
ffmpeg -i mono.mp3 -ac 2 stereo.mp3

Mix Audio Tracks

# Replace audio track
ffmpeg -i video.mp4 -i audio.mp3 -c:v copy -map 0:v:0 -map 1:a:0 output.mp4

# Mix two audio tracks
ffmpeg -i video.mp4 -i audio2.mp3 \
  -filter_complex "[0:a][1:a]amix=inputs=2:duration=first" \
  -c:v copy output.mp4

# Mix with volume control
ffmpeg -i video.mp4 -i bgm.mp3 \
  -filter_complex "[0:a]volume=1.0[voice];[1:a]volume=0.3[music];[voice][music]amix=inputs=2:duration=first" \
  -c:v copy output.mp4

Read the full file on GitHub · 168 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 168 lines · 21 tokens per session scan A 001943d16329

Subscribe to this mod's changes

ffmpeg-audio-processing is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,267 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.