What problem does it solve? Audio analysis often requires visual inspection of frequency content, tempo, and structure, but setting up spectrogram tooling in Python or DAW plugins is slow. This Skill wraps the songsee CLI to produce spectrograms and multi-panel audio feature images directly from audio files. ## Core Features & Use Cases - Spectrogram Generation: Render standard, mel-scaled, and styled spectrograms from WAV or MP3 files with configurable FFT window, hop size, and frequency range. - Multi-Panel Feature Grids: Combine chroma, HPSS, self-similarity, loudness, tempogram, MFCC, and spectral flux visualizations into a single image. - Time Slicing and Format Control: Extract specific time ranges with --start and --duration, and output PNG or JPG at custom dimensions. - Use Case: Compare two synthesized audio outputs by generating side-by-side mel spectrograms, then inspect the images with vision analysis to verify frequency content and detect artifacts. ## Quick Start Ask the assistant to generate a mel spectrogram of your audio file, for example: create a spectrogram of track.mp3 and save it as spectrogram.png.
