Generate spectrograms and feature-panel visualizations from audio files using the songsee CLI.
npx skills add https://github.com/Dolonia333/dolo.ai --skill songsee-dolonia333
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/Dolonia333/dolo.ai/tree/main/skills/songsee Command: npx skills add https://github.com/Dolonia333/dolo.ai --skill songsee-dolonia333
Audio visualization and feature extraction from raw audio data, enabling rapid exploration and presentation of spectral content and descriptors.
Process an audio file to generate spectrograms and feature panels using the songsee CLI.
High-intent search queries and answers about installing and using this skill.
Generate audio spectrograms by processing audio files through the songsee CLI, which visualizes frequency content over time. This produces image outputs and plots suitable for music analysis, podcast processing, and audio research workflows.
Audio feature panels visualize descriptors such as mel, chroma, mfcc, hpss, and loudness from audio files. These multi-panel visualizations enable rapid exploration of spectral content for music analysis and audio research tasks.
Yes, the songsee binary must be installed to process audio streams and files. The CLI requires this local installation to generate spectrograms and feature-panel visualizations from your audio inputs.
Audio visualization supports podcast production workflows by generating spectrograms and feature panels from audio files. This allows quick visual inspection of frequency content and descriptors needed for podcast processing.
Extract spectral descriptors from raw audio data by applying the songsee CLI to generate multi-panel feature visualizations. This method provides rapid exploration of mel, chroma, mfcc, hpss, and loudness descriptors for audio research.
okgoogle13Generate React component files from Figma Inspect panel details.
StarlitnightlyGenerate publication-quality plots with matplotlib and seaborn.
Generous-CorpMeasure audio metrics and verify DSP contracts in headless environments.
yunseo-kimGenerate spectrograms and feature-panel visualizations from audio files.
