What problem does it solve? Analyzing audio content visually requires specialized tooling; this Skill turns audio files into spectrograms and multi-panel feature visualizations (mel, chroma, MFCC, and more) with a single command, making audio structure, tempo, and timbre inspectable as images. ## Core Features & Use Cases - Spectrogram Generation: Render standard or mel-scaled spectrograms from WAV and MP3 files, with optional ffmpeg support for other formats. - Multi-Panel Feature Grids: Combine up to nine visualization types (chroma, HPSS, self-similarity, loudness, tempogram, MFCC, spectral flux) into a single image. - Flexible Output Control: Slice audio by time range, choose color palettes, set image dimensions, and output PNG or JPG. - Use Case: Compare two synthesized audio outputs by generating side-by-side mel spectrograms, then inspect the images with a vision model to verify the synthesis pipeline. ## Quick Start Use the songsee skill to generate a mel spectrogram and chroma visualization from my track.mp3 file and save it as a PNG image.
