mcpField
A
audio-extract

audio-extract

github.com/agntswrmCreative & media639 installsUpdated 34w ago
Repository

About audio-extract

audio-extract is a skill for extracting an audio track from a video file with bundled ffmpeg. It is intended for media workflows such as preparing audio for transcription, and runs locally without API keys or external services.

Key features

  1. 01Extract audio from video files or URLs
  2. 02Choose MP3 or WAV output
  3. 03Set an output path or directory
  4. 04Use bundled ffmpeg locally

Use cases

  1. 01Prepare a video interview for transcription
  2. 02Save a video's audio as a separate file

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agntswrm/agent-media --skill audio-extract

After installing, type/audio-extractin Claude Code to confirm it loaded.

Details

From the project README

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

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

Inputs

OptionRequiredDescription
--inYesInput video file path or URL (supports mp4, webm, mkv, avi, mov)
--formatNoOutput audio format: mp3 (default) or wav
--outNoOutput 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):

npx agent-media@latest audio extract --in video.mp4

Extract audio as WAV:

npx agent-media@latest audio extract --in video.mp4 --format wav

Custom output directory:

npx agent-media@latest 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)
npx agent-media@latest audio extract --in interview.mp4 --format mp3
# Output: extracted_xxx.mp3

# Step 2: Transcribe the audio (cloud API)
npx agent-media@latest 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.

Comments

Markdown supported