Generate spectrograms and feature-panel visualizations from audio files.
npx skills add https://github.com/estebanrfp/gos --skill songsee-estebanrfp
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/estebanrfp/gos/tree/main/skills/songsee Command: npx skills add https://github.com/estebanrfp/gos --skill songsee-estebanrfp
songsee turns audio into visual representations so you can inspect spectral content, rhythm, timbre, and other features without manually building analysis pipelines.
Use the songsee skill to generate a multi-panel visualization from the attached audio file and save it as an image.
High-intent search queries and answers about installing and using this skill.
You can generate a spectrogram for music analysis by using the songsee skill to process native WAV or MP3 audio files and produce clear frequency-over-time visualizations without manually building analysis pipelines.
For waveform comparison, you can visualize multiple extracted audio features including mel, chroma, HPSS, self-similarity, loudness, tempogram, MFCC, and flux combined into a single multi-panel image.
The audio visualization CLI natively supports WAV and MP3 decoding, and it offers optional ffmpeg support to process additional audio formats for spectrogram and feature-panel generation.
The best way to isolate time ranges and review specific audio sections is using the songsee CLI's time-sliced review workflows, which apply configurable sizing and frequency controls to inspect targeted segments.
Yes, you can configure visualization, sizing, frequency, and export controls when generating audio feature extraction visuals to tailor the multi-panel output for presentations and analysis notes.
TitoPrauseeGenerate spectrogram and audio feature visualizations from audio files.
kcns008Generate spectrogram and feature-panel visualizations from audio files.
me2DocGenerate spectrograms and audio feature panels from audio files using songsee CLI.
erichowensRender real-time audio-responsive WebGL visualizations using Butterchurn presets and Web Audio FFT data.
