What problem does it solve? Turning raw audio into visual representations like spectrograms normally requires writing signal-processing code. This Skill wraps the songsee CLI so you can produce spectrograms and multi-panel audio feature visualizations with a single command. ## Core Features & Use Cases - Spectrogram Generation: Render a spectrogram from any audio file with one command, with control over palette, size, FFT window, and frequency range. - Multi-Panel Feature Grids: Combine visualizations such as mel, chroma, HPSS, self-similarity, loudness, tempogram, MFCC, and flux into a single grid image. - Time Slicing and Streaming: Extract a specific time window with --start and --duration, or pipe audio via stdin and output JPG or PNG. - Use Case: A music researcher wants to compare the spectral content of a chorus across tracks. They generate mel and chroma panels for an 8-second slice of each song and place the images side by side in a report. ## Quick Start Ask the assistant to generate a spectrogram of your audio file, for example: create a spectrogram of track.mp3 using songsee and save it as a PNG.
