audio-extraction

What problem does it solve?

This Skill solves the problem of turning video files and podcast feeds into clean, correctly formatted, and well-tagged audio collections without manual, error-prone transcoding.

Core Features & Use Cases

• Audio extraction from video (yt-dlp/ffmpeg): Extract best-quality audio tracks from YouTube and convert them to MP3/FLAC/AAC/Opus/WAV for playback or archival.
• Batch processing and media cleanup: Convert multiple files, split by chapters, trim segments, merge tracks, and normalize loudness so everything sounds consistent.
• Metadata tagging for library hygiene: Embed thumbnails and tags, generate ID3 metadata (e.g., artist/album/title), and improve searchability and organization with consistent naming conventions.
• Speech-ready extraction for transcription: Produce mono 16kHz WAV optimized for speech-to-text workflows from video sources.
• Use case: Build a personal music and podcast library by extracting audio from a folder of recordings, converting to MP3/Opus as appropriate, normalizing loudness, and tagging files from filename patterns.

Quick Start

Use the audio-extraction skill to download the highest-quality MP3 audio from a YouTube video while embedding metadata and the thumbnail.