skills.rest
CHENHUI-X
CHENHUI-XCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

songsee

Generate spectrograms and audio feature visualizations from audio files via CLI.

Updated Jul 3, 2026
Search Tags:#cli#visualization#audio#chroma#spectrogram#mfcc#music analysis
One-click install
npx skills add https://github.com/CHENHUI-X/toolbox --skill songsee-chenhui-x
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/CHENHUI-X/toolbox/tree/main/official-skills/media/songsee
Command: npx skills add https://github.com/CHENHUI-X/toolbox --skill songsee-chenhui-x

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Analyzing audio content visually requires specialized tooling; this Skill turns audio files into spectrograms and multi-panel feature visualizations (mel, chroma, MFCC, and more) with a single CLI command, making audio characteristics inspectable as images. ## Core Features & Use Cases - Spectrogram Generation: Render standard, mel-scaled, and styled spectrograms from WAV or MP3 files with configurable FFT window, hop size, and frequency range. - Multi-Panel Feature Grids: Combine up to nine visualization types (chroma, HPSS, self-similarity, loudness, tempogram, MFCC, spectral flux) into a single grid image. - Time Slicing & Flexible I/O: Extract specific time ranges with --start/--duration, read audio from stdin, and output PNG or JPG at custom dimensions. - Use Case: Compare two synthesized audio outputs by generating side-by-side mel spectrograms, then inspect the images with a vision model to verify frequency content and detect artifacts. ## Quick Start Generate a mel spectrogram from the attached audio file 'track.mp3' and save it as a PNG image.

Frequently Asked Questions about songsee

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

FAQPage Schema
How do I generate a spectrogram from an MP3 file?▼

Run songsee with the audio file as argument, for example 'songsee track.mp3 -o spectrogram.png'. WAV and MP3 are decoded natively, and you can control output size, color style, and frequency range with flags.

What audio visualization types does songsee support?▼

songsee supports nine types: spectrogram, mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, and flux. Pass them comma-separated via --viz to render multiple panels as a grid in one image.

Does songsee support audio formats other than WAV and MP3?▼

WAV and MP3 are decoded natively by songsee. For other formats such as FLAC or AAC, you need ffmpeg installed so the audio can be converted before visualization.

How do I visualize only part of an audio file?▼

Use the --start and --duration flags to select a time slice, for example 'songsee track.mp3 --start 12.5 --duration 8' renders an 8-second segment starting at 12.5 seconds.

Can songsee read audio from stdin?▼

Yes, pipe audio via stdin using '-' as the input, such as 'cat track.mp3 | songsee - --format png -o out.png'. This is useful for chaining with other command-line audio tools.

Related Skills

Explore More Design & Creative Skills→
NousResearchNousResearch
239.1k

songsee

Generate spectrograms and audio feature visualizations from audio files.

Official
Basic
MLT-OSSMLT-OSS
14

songsee

Generate spectrograms and audio feature visualizations from audio files via CLI.

Official
Basic
xjtulycxjtulyc
33

librosa-audio

Extract MIR features from audio and retrieve similar tracks via k-NN.

Community
Intermediate
taracodlabstaracodlabs
799

songsee

Generate mel spectrograms, chromagrams, and MFCC plots from audio files using librosa.

Official
Basic