skills.rest
superfhp
superfhpCOMMUNITY
Explore all skills by this author →
GitHub

songsee

Generate spectrograms and multi-panel audio feature visualizations from audio files via CLI.

Updated May 13, 2026
Search Tags:#cli#chroma#spectrogram#mfcc#audio visualization#music analysis#mel
One-click install
npx skills add https://github.com/superfhp/lumi-agent-body --skill songsee-superfhp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/superfhp/lumi-agent-body/tree/main/skills/media/songsee
Command: npx skills add https://github.com/superfhp/lumi-agent-body --skill songsee-superfhp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Analyzing audio content typically requires opening a DAW or writing custom signal-processing code. This Skill turns any audio file into visual spectrograms and feature plots (mel, chroma, MFCC, and more) with a single CLI command, making audio inspection fast and scriptable. ## 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 image. - Time Slicing & Piping: Visualize a specific segment with --start/--duration, or stream audio via stdin for pipeline integration. - Use Case: Compare two synthesized audio outputs by generating side-by-side mel spectrograms, then inspect the images with a vision model to verify the synthesis pipeline. ## Quick Start Ask the assistant to generate a mel spectrogram of your audio file, for example: "Create a spectrogram and chroma visualization of track.mp3 and save it as analysis.png."

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 palette, and frequency range with flags.

What audio visualization types does songsee support?▼

songsee supports nine visualization types: spectrogram, mel, chroma, hpss, self-similarity, loudness, tempogram, MFCC, and spectral flux. Pass them as comma-separated values to --viz to render multiple panels in a single grid image.

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

WAV and MP3 are decoded natively without extra tools. For other formats such as FLAC, AAC, or OGG, you need ffmpeg installed so songsee can decode them.

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 -o slice.jpg. This renders only the specified 8-second segment beginning at 12.5 seconds.

Can I pipe audio into songsee from stdin?▼

Yes, pass a dash as the input and stream audio via stdin, for example: cat track.mp3 | songsee - --format png -o out.png. This makes it easy to integrate songsee into shell pipelines.

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
dkyazzentwatwadkyazzentwatwa
86

audio-analyzer

Analyze audio tempo, key, loudness, and frequency with waveform and spectrogram visualizations.

Community
Intermediate
taracodlabstaracodlabs
799

songsee

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

Official
Basic