processing-audio

Convert and process audio files with ffmpeg for format, sample-rate, and channel changes.

1|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/Open330/agt --skill processing-audio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: processing-audio
Source: https://github.com/Open330/agt/tree/main/ml/audio-processor
Command: npx skills add https://github.com/Open330/agt --skill processing-audio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, jq, bc, and includes scripts (resource) components.

What problem does it solve?

Converting and processing audio files across formats, sample rates, and channels is time-consuming and error-prone. This skill automates these tasks using ffmpeg to streamline audio workflows.

Core Features & Use Cases

  • Format conversion: wav, mp3, opus, m4a, and more.
  • Sample-rate and channel adjustments: convert to 8kHz/16kHz/22.05kHz/44.1kHz/48kHz and mono or stereo.
  • Segment and batch processing: split by duration or timestamps, or process all files in a directory.
  • Automation-friendly: Claude can trigger the integration automatically for relevant requests.

Quick Start

Convert sample.mp3 to sample.wav at 16kHz mono.

Frequently Asked Questions about processing-audio

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch convert audio files to wav at 16kHz mono for machine learning datasets?

Yes, you can split audio files by specifying duration or timestamps. This skill uses ffmpeg to segment audio files, enabling batch processing of directories and precise extraction of audio chunks for speech recognition pipelines.

Does ffmpeg batch audio processing support converting between mp3, opus, and m4a formats?

You need ffmpeg (including ffprobe) and jq installed to perform audio transformations. The skill also requires bc for calculating size calculations when reporting results during batch processing and format conversion.

What is the best way to prepare audio for speech recognition pipelines using ffmpeg?

Automate audio format conversion with ffmpeg to streamline time-consuming workflows. This skill handles directory batch processing, sample-rate adjustments, and channel conversions, reducing manual errors across wav, mp3, opus, and m4a formats.

Can I split audio files by duration or timestamps for batch processing?

Yes, you can split audio files by specifying duration or timestamps. This skill uses ffmpeg to segment audio files, enabling batch processing of directories and precise extraction of audio chunks for speech recognition pipelines.

Do I need jq and bc installed to automate audio format conversion with ffmpeg?

You need ffmpeg (including ffprobe) and jq installed to perform audio transformations. The skill also requires bc for calculating size calculations when reporting results during batch processing and format conversion.