skills.rest
moistalgia
moistalgiaCOMMUNITY
Explore all skills by this author →
GitHub

songsee

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

Updated Jul 27, 2026
Search Tags:#cli#visualization#ffmpeg#music#spectrogram#mfcc#audio analysis
One-click install
npx skills add https://github.com/moistalgia/hermes-tools --skill songsee-moistalgia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/moistalgia/hermes-tools/tree/main/skills-from-hermes/media/songsee
Command: npx skills add https://github.com/moistalgia/hermes-tools --skill songsee-moistalgia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Analyzing audio content visually requires specialized tooling; this Skill turns any audio file into spectrograms and feature visualizations (mel, chroma, MFCC, and more) with a single command, making audio structure, pitch, tempo, and onsets inspectable as images. ## Core Features & Use Cases - Spectrogram Generation: Render standard, mel-scaled, and harmonic/percussive-separated spectrograms from WAV or MP3 files. - Multi-Panel Feature Grids: Combine up to nine visualization types (chroma, self-similarity, loudness, tempogram, MFCC, flux) into a single image. - Time Slicing and Styling: Extract specific time ranges, choose color palettes, and control FFT window, hop size, and frequency range. - 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 Generate a mel spectrogram from my track.mp3 file 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, and it renders a spectrogram image. Use -o to set the output path and --format to choose png or jpg.

How to visualize multiple audio features in one image?▼

Pass comma-separated visualization types with the --viz flag, such as --viz spectrogram,mel,chroma,mfcc. Songsee renders all requested panels as a grid in a single output image.

What audio formats does songsee support?▼

Songsee decodes WAV and MP3 files natively without extra tools. For other formats such as FLAC or AAC, ffmpeg must be installed on the system to handle decoding.

Can I generate a spectrogram of only part of an audio file?▼

Yes, use the --start and --duration flags to slice the audio, for example --start 12.5 --duration 8 to visualize an 8-second segment beginning at 12.5 seconds.

What are the limitations of CLI spectrogram generation?▼

Songsee produces static images rather than interactive plots, so zooming or hovering over frequency data is not possible. It also requires a Go toolchain for installation and ffmpeg for non-WAV/MP3 formats.

Related Skills

Explore More Design & Creative Skills→
NousResearchNousResearch
239.1k

songsee

Generate spectrograms and audio feature visualizations from audio files.

Official
Basic
GitnappGitnapp

songsee

Generate spectrograms and feature visualizations from audio files using songsee.

Community
Intermediate
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