Learn-skills.dev audio-extract

Extracts audio track from a video file. Use when you need to get audio from video, prepare audio for transcription, or separate audio from video content. Runs locally with no API key required.

install

source · Clone the upstream repo

git clone https://github.com/NeverSight/learn-skills.dev

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/NeverSight/learn-skills.dev "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/skills-md/agntswrm/agent-media/audio-extract" ~/.claude/skills/neversight-learn-skills-dev-audio-extract && rm -rf "$T"

manifest: data/skills-md/agntswrm/agent-media/audio-extract/SKILL.md

source content

Audio Extract

Extracts the audio track from a video file. This is a local operation using the bundled ffmpeg binary - no API keys or external services required.

Command

agent-media audio extract --in <path> [options]

Inputs

Option Required Description

--in

Yes

Input video file path or URL (supports mp4, webm, mkv, avi, mov)

--format

Output audio format:

mp3

(default) or

wav

--out

Output path, filename or directory (default: ./)

Output

Returns a JSON object with the extracted audio file:

{
  "ok": true,
  "media_type": "audio",
  "action": "extract",
  "provider": "local",
  "output_path": "extracted_123_abc.mp3",
  "mime": "audio/mpeg",
  "bytes": 24779
}

Examples

Extract audio as MP3 (default):

agent-media audio extract --in video.mp4

Extract audio as WAV:

agent-media audio extract --in video.mp4 --format wav

Custom output directory:

agent-media audio extract --in video.mp4 --out ./audio-files

Use Case: Video Transcription Workflow

Since transcription services work best with audio files (smaller uploads, faster processing), use this workflow:

# Step 1: Extract audio from video (local, instant)
agent-media audio extract --in interview.mp4 --format mp3
# Output: extracted_xxx.mp3

# Step 2: Transcribe the audio (cloud API)
agent-media audio transcribe --in extracted_xxx.mp3 --provider fal

Provider

This action uses the local provider with bundled ffmpeg (via

ffmpeg-static

). No API keys required.