Generate spectrograms and multi-panel audio feature visualizations from audio files.
npx skills add https://github.com/devMoez/titan --skill songsee-devmoez
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/devMoez/titan/tree/main/skills/media/songsee Command: npx skills add https://github.com/devMoez/titan --skill songsee-devmoez
Songsee turns audio files into visual spectrograms and interpretable audio feature maps, saving you from manual, error-prone analysis when studying timbre, pitch content, onset behavior, or rhythm.
Run songsee on your audio file to generate a spectrogram image output.
High-intent search queries and answers about installing and using this skill.
You can generate a spectrogram from an audio file by running the songsee CLI, which computes frequency energy over time and writes the resulting visualization to a common image format for rapid analysis.
You can visualize mel-scaled spectrograms, chroma, MFCCs, spectral flux, loudness, and tempogram representations to inspect timbre, pitch content, onset behavior, and rhythm from your audio files.
Yes, you need Go installed in your environment, as the songsee CLI is a Go dependency required to compute the audio feature representations and generate the output images.
Yes, you can export single panels or multi-panel grids for a specific time window using the batch-friendly CLI, making it easy to inspect audio segments during debugging or documentation.
The best way to compare audio feature representations is generating multi-panel visualizations that display harmonic, percussive, and self-similarity maps side-by-side from the same input audio file.
A limitation of CLI-based music spectrogram rendering is that it outputs static image files, meaning you cannot dynamically interact with or zoom into the visualizations after generation.
erichowensRender real-time audio-responsive WebGL visualizations using Butterchurn presets and Web Audio FFT data.
AlvaroBianoGenerate spectrogram, mel, chroma, hpss, mfcc visualizations from audio files to PNG/JPG using songsee CLI.
RheasilviaGenerate spectrograms and audio feature analyses from audio files via command line.
CUexterGenerate spectrograms and multi-panel audio feature visualizations from audio files.
