Audio Extractor

CommunityPopular

dp-archive

audio-extractor

Extract audio from videos and download audio-only content from 1500+ websites using yt-dlp. Converts to MP3, M4A, FLAC, WAV, or OPUS with embedded metadata and cover art. Use when the user wants to extract audio from videos, download podcasts, download music from YouTube/SoundCloud/Bandcamp, convert video to audio, or batch download playlist audio. Triggers on requests like 'extract audio', 'download as MP3', 'get the audio from this video', 'download this podcast', 'download music', 'convert to FLAC'.

Overview

Publisher	dp-archive
Repository	`archive`
Skill name	`audio-extractor`
Stars	1.1K
Forks	100
Bundled files	1
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by dp-archive on GitHub. Read the source before you install it.

Installation

Install the Audio Extractor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/dp-archive/archive/tree/main/seed_skills/audio-extractor
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/dp-archive/archive.git /tmp/archive
mkdir -p .claude/skills
cp -r /tmp/archive/seed_skills/audio-extractor .claude/skills/audio-extractor

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Audio Extractor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Audio Extractor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Audio Extractor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Audio Extractor

Extract pure audio from videos and download audio content. Supports format conversion, metadata embedding, and batch playlist processing.

Prerequisites

Executor: Must use the remotion executor (provides yt-dlp, ffmpeg, deno)
JS Runtime: deno is required for YouTube extraction (yt-dlp 2025+ default). The remotion executor includes deno.
ffmpeg: Required for audio format conversion and metadata embedding. Included in remotion executor.

Limitations

Issue	Detail
YouTube rate limiting	Server IPs are frequently rate-limited by YouTube. If you get "This content isn't available, try again later", wait ~1 hour or ask the user to upload the audio file directly.
YouTube JS runtime	yt-dlp requires deno for YouTube. Without it: `No supported JavaScript runtime could be found`.
Geo-restrictions	Some content may be region-locked. Use `--geo-bypass` flag.
Authentication	Some platforms require cookies. Use `--cookies-from-browser` or `--cookies cookies.txt`.

Fallback strategy: If YouTube download fails, suggest the user upload the audio file directly or provide a direct audio URL.

Quick Start

bash
# Extract audio (best quality, original format)
yt-dlp -x "URL"

# Extract as MP3
yt-dlp -x --audio-format mp3 "URL"

# MP3 with metadata and cover art
yt-dlp -x --audio-format mp3 --embed-metadata --embed-thumbnail "URL"

Audio Formats

Format Selection

Format	Command	Use Case
MP3	`--audio-format mp3`	Universal compatibility
M4A/AAC	`--audio-format m4a`	Apple devices, good quality/size
FLAC	`--audio-format flac`	Lossless, archival
WAV	`--audio-format wav`	Uncompressed, editing
OPUS	`--audio-format opus`	Best quality/size ratio
Vorbis	`--audio-format vorbis`	Open source, OGG container
Best	`--audio-format best`	Keep original (no conversion)

Quality Control

bash
# VBR quality (0=best, 10=worst)
yt-dlp -x --audio-format mp3 --audio-quality 0 "URL"

# Specific bitrate
yt-dlp -x --audio-format mp3 --audio-quality 320K "URL"
yt-dlp -x --audio-format mp3 --audio-quality 192K "URL"

# FLAC (lossless - quality setting ignored)
yt-dlp -x --audio-format flac "URL"

Metadata Embedding

Embed All Metadata

bash
# Metadata + thumbnail as cover art
yt-dlp -x --audio-format mp3 \
       --embed-metadata \
       --embed-thumbnail \
       "URL"

What Gets Embedded

Title
Artist/Uploader
Album (playlist name if applicable)
Track number (playlist index)
Upload date
Description
Thumbnail as cover art

Custom Metadata

bash
# Override artist
yt-dlp -x --audio-format mp3 \
       --embed-metadata \
       --parse-metadata "uploader:%(artist)s" \
       "URL"

# Set album name
yt-dlp -x --audio-format mp3 \
       --embed-metadata \
       --parse-metadata "playlist:%(album)s" \
       "URL"

Playlist/Batch Processing

Download Full Playlist as Audio

bash
# Basic playlist extraction
yt-dlp -x --audio-format mp3 "PLAYLIST_URL"

# With numbering and organization
yt-dlp -x --audio-format mp3 \
       --embed-metadata --embed-thumbnail \
       -o "%(playlist)s/%(playlist_index)02d - %(title)s.%(ext)s" \
       "PLAYLIST_URL"

# Skip already downloaded
yt-dlp -x --audio-format mp3 \
       --download-archive downloaded.txt \
       "PLAYLIST_URL"

Selective Download

bash
# First 10 tracks
yt-dlp -x --audio-format mp3 -I 1:10 "PLAYLIST_URL"

# Specific tracks
yt-dlp -x --audio-format mp3 -I 1,5,10 "PLAYLIST_URL"

# Last 5 tracks
yt-dlp -x --audio-format mp3 -I -5: "PLAYLIST_URL"

Output Naming

Template Variables

Variable	Description	Example
`%(title)s`	Track title	Song Name
`%(uploader)s`	Artist/Channel	Artist Name
`%(playlist)s`	Album/Playlist	My Playlist
`%(playlist_index)s`	Track number	1
`%(upload_date)s`	Release date	20231215
`%(ext)s`	Extension	mp3

Common Patterns

bash
# Artist - Title
yt-dlp -x -o "%(uploader)s - %(title)s.%(ext)s" "URL"

# Album folder with track numbers
yt-dlp -x -o "%(playlist)s/%(playlist_index)02d - %(title)s.%(ext)s" "PLAYLIST_URL"

# Date-organized
yt-dlp -x -o "%(upload_date>%Y-%m)s/%(title)s.%(ext)s" "URL"

Platform-Specific

YouTube Music / YouTube

bash
# Standard extraction
yt-dlp -x --audio-format mp3 --embed-metadata --embed-thumbnail "URL"

# For music videos, prefer audio stream
yt-dlp -f "bestaudio" -x --audio-format mp3 "URL"

SoundCloud

bash
# Direct audio (often already MP3)
yt-dlp -x "https://soundcloud.com/artist/track"

# Playlist/album
yt-dlp -x --audio-format mp3 \
       -o "%(uploader)s - %(album)s/%(playlist_index)02d - %(title)s.%(ext)s" \
       "https://soundcloud.com/artist/sets/album"

Bandcamp

bash
# Full album with metadata
yt-dlp -x --audio-format flac \
       --embed-metadata --embed-thumbnail \
       -o "%(album)s/%(track_number)02d - %(track)s.%(ext)s" \
       "https://artist.bandcamp.com/album/name"

Podcasts

bash
# Single episode
yt-dlp -x --audio-format mp3 --embed-metadata "EPISODE_URL"

# Full podcast feed (RSS)
yt-dlp -x --audio-format mp3 \
       -o "%(playlist)s/%(upload_date)s - %(title)s.%(ext)s" \
       --download-archive podcasts.txt \
       "RSS_FEED_URL"

# Apple Podcasts
yt-dlp -x --audio-format mp3 \
       --embed-metadata \
       "https://podcasts.apple.com/..."

Bilibili

bash
yt-dlp -x --audio-format mp3 \
       --cookies-from-browser chrome \
       "https://bilibili.com/video/BV..."

Advanced Options

Parallel Downloads

bash
# Faster playlist downloads
yt-dlp -x --audio-format mp3 \
       --concurrent-fragments 4 \
       "PLAYLIST_URL"

Post-Processing

bash
# Normalize audio volume
yt-dlp -x --audio-format mp3 \
       --postprocessor-args "ffmpeg:-af loudnorm" \
       "URL"

# Trim silence
yt-dlp -x --audio-format mp3 \
       --postprocessor-args "ffmpeg:-af silenceremove=1:0:-50dB" \
       "URL"

Split by Chapters

bash
# Split video into separate audio files by chapter
yt-dlp -x --audio-format mp3 \
       --split-chapters \
       -o "chapter:%(section_title)s.%(ext)s" \
       "URL"

Complete Examples

Extract audio from YouTube playlist as high-quality MP3:

bash
yt-dlp -x --audio-format mp3 --audio-quality 0 \
       --embed-metadata --embed-thumbnail \
       -o "%(playlist)s/%(playlist_index)02d - %(title)s.%(ext)s" \
       --download-archive downloaded.txt \
       "https://youtube.com/playlist?list=..."

Download podcast episode:

bash
yt-dlp -x --audio-format mp3 \
       --embed-metadata \
       -o "%(uploader)s - %(title)s.%(ext)s" \
       "https://podcasts.apple.com/..."

Extract FLAC from Bandcamp album:

bash
yt-dlp -x --audio-format flac \
       --embed-metadata --embed-thumbnail \
       -o "%(album)s/%(track_number)02d - %(track)s.%(ext)s" \
       "https://artist.bandcamp.com/album/..."

Extract audio from local video file:

bash
ffmpeg -i video.mp4 -vn -acodec libmp3lame -q:a 0 audio.mp3

Troubleshooting

Issue	Solution
"ffmpeg not found"	Install ffmpeg: `brew install ffmpeg` / `apt install ffmpeg`
No cover art	Add `--embed-thumbnail` (requires ffmpeg)
Wrong metadata	Use `--parse-metadata` to remap fields
Poor quality	Use `--audio-quality 0` or lossless format

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

scripts/extract_audio.py5 KB

Frequently asked questions

What does the Audio Extractor AI skill do?

Why use Audio Extractor on TypingMind?

Because you install it once and use it with any model. Audio Extractor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Audio Extractor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dp-archive/archive/tree/main/seed_skills/audio-extractor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Audio Extractor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Audio Extractor?

As many as you like. As long as a model supports skills, you can use Audio Extractor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Audio Extractor AI skill free?

Yes. It is published on GitHub by dp-archive under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Brag Slim

NousResearch

OrganizationPopular

Launch video from a project or URL, upstream-maintained.

Brag

Project launch video via Hyperframes, upstream-maintained.

Comfyui

Generate images, video, and audio via diffusion workflows.

Heartmula

HeartMuLa: Suno-like song generation from lyrics + tags.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Audio Extractor

Prerequisites

Limitations

Quick Start

Audio Formats

Format Selection

Quality Control

Metadata Embedding

Embed All Metadata

What Gets Embedded

Custom Metadata

Playlist/Batch Processing

Download Full Playlist as Audio

Selective Download

Output Naming

Template Variables

Common Patterns

Platform-Specific

YouTube Music / YouTube

SoundCloud

Bandcamp

Podcasts

Bilibili

Advanced Options

Parallel Downloads

Post-Processing

Split by Chapters

Complete Examples

Troubleshooting

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now