skills.rest
yakeworld
yakeworldCOMMUNITY
Explore all skills by this author →
GitHub

songsee

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

6|1|Updated May 11, 2026
Search Tags:#cli#mp3#chroma#spectrogram#songsee#audio visualization#mel
One-click install
npx skills add https://github.com/yakeworld/Synthos --skill songsee-yakeworld
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/yakeworld/Synthos/tree/main/skills/extended/external-automation/automation-skills/media/songsee
Command: npx skills add https://github.com/yakeworld/Synthos --skill songsee-yakeworld

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires go, ffmpeg.

What problem does it solve? Analyzing audio content for debugging synthesis, comparing outputs, or documenting pipelines requires visual representations of frequency and temporal features, which are tedious to produce manually. ## Core Features & Use Cases - Spectrogram Generation: Create standard, mel-scaled, and chroma spectrograms from WAV or MP3 files via the songsee Go CLI. - Multi-Panel Grids: Combine up to nine visualization types (spectrogram, mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, flux) into a single grid image. - Time Slicing: Visualize a specific segment of audio using start and duration parameters, with customizable color palettes and image dimensions. - Use Case: When debugging an audio synthesis pipeline, generate a five-panel grid of spectrogram, mel, chroma, tempogram, and flux views of a track, then feed the image to a vision analysis tool for automated inspection. ## Quick Start Generate a spectrogram image from my track.mp3 file and save it as spectrogram.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 the songsee CLI with the audio file as input, for example songsee track.mp3 -o spectrogram.png. MP3 and WAV files are decoded natively, and you can control output format, dimensions, and color style with flags.

What audio visualization types does songsee support?▼

Songsee supports nine visualization types: spectrogram, mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, and flux. Passing multiple comma-separated types via the --viz flag renders them as a grid in a single image.

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

WAV and MP3 are decoded natively without extra tools. For other formats, you must install ffmpeg 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, such as songsee track.mp3 --start 12.5 --duration 8. The slice must fall within the actual audio duration or the request is rejected.

Why does songsee reject my --viz parameter?▼

The --viz value must be one of the nine valid types: spectrogram, mel, chroma, hpss, selfsim, loudness, tempogram, mfcc, or flux. Invalid values like abbreviations are rejected with an error listing the valid options and recovery suggestions.

Related Skills

Explore More Design & Creative Skills→
NousResearchNousResearch
239.1k

songsee

Generate spectrograms and audio feature visualizations from audio files.

Official
Basic
gigagiovagigagiova

songsee

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

Community
Intermediate
wimpysworldwimpysworld
716

audio-metrics

Defines ffmpeg audio metrics for spectral statistics, loudness, and level measurements.

Official
Intermediate
taracodlabstaracodlabs
799

songsee

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

Official
Basic