What types of feature panels can be generated?

The skill can render a variety of panels including mel-spectrograms, chroma features, harmonic-percussive source separation (HPSS), self-similarity matrices, loudness, tempograms, MFCCs, and spectral flux.

Can I visualize specific sections of a long audio file?

Yes, you can use the --start and --duration flags to specify a precise time slice, allowing you to render visualizations for specific segments rather than the whole track.

What audio formats does Songsee support?

Songsee natively decodes WAV and MP3 files. For other formats such as FLAC or OGG, it automatically utilizes FFmpeg if it is installed on your system.

How do I use this within Claude Code?

Once installed, you can ask Claude to visualize an audio file in your directory, and it will use the songsee command-line interface to generate the requested plots and images.

Are the visual styles customizable?

Absolutely. You can choose from multiple color palettes including classic, magma, inferno, viridis, and gray to suit your documentation or UI needs.

Songsee Audio Visualization

Name: Songsee Audio Visualization
Author: drshailesh88

bydrshailesh88

データサイエンスとML

Generates detailed spectrograms and multi-panel audio feature visualizations for technical analysis and documentation.

概要

Songsee is a specialized utility for converting audio data into comprehensive visual representations, including spectrograms, mel-frequency cepstral coefficients (MFCCs), and chroma features. It provides developers and audio engineers with a streamlined way to inspect audio characteristics like loudness, tempograms, and spectral flux directly within their workflow. Whether you are debugging audio processing algorithms, preparing data for machine learning, or creating visual assets for music research, this skill automates the complex rendering process with customizable palettes and precise time-slicing capabilities.

主な機能

0 GitHub stars
Generate multi-panel grids including Mel, Chroma, HPSS, and Self-similarity plots
Support for precise time-slicing to visualize specific segments of audio files
Create high-resolution spectrograms with customizable styles like Magma and Viridis
Native decoding for WAV and MP3 with FFmpeg support for extended formats
Flexible output configurations for custom dimensions, FFT windowing, and frequency ranges

ユースケース

Generating visual datasets for training and debugging audio machine learning models
Analyzing frequency characteristics and harmonic content for audio engineering
Creating high-quality waveform and spectral documentation for music production tools

概要

主な機能

0 GitHub stars
Generate multi-panel grids including Mel, Chroma, HPSS, and Self-similarity plots
Support for precise time-slicing to visualize specific segments of audio files
Create high-resolution spectrograms with customizable styles like Magma and Viridis
Native decoding for WAV and MP3 with FFmpeg support for extended formats
Flexible output configurations for custom dimensions, FFT windowing, and frequency ranges

ユースケース

Generating visual datasets for training and debugging audio machine learning models
Analyzing frequency characteristics and harmonic content for audio engineering
Creating high-quality waveform and spectral documentation for music production tools