What audio formats does songsee support?

The skill natively decodes WAV and MP3 files. For other formats, it utilizes ffmpeg if it is installed on your system.

What types of audio features can be visualized?

You can generate a grid of visualizations including spectrograms, mel, chroma, HPSS, self-similarity, loudness, tempograms, and MFCCs.

Does this skill require external software installation?

Yes, this skill requires the songsee CLI tool. It can be installed via Homebrew using 'brew install steipete/tap/songsee'.

Can I visualize specific parts of a long audio track?

Yes, you can use the --start and --duration flags to target and render visualizations for specific time slices within a file.

Are the spectrogram colors customizable?

Absolutely. You can choose from several color palettes using the --style flag, including classic, magma, inferno, viridis, and gray.

Audio Visualization with Songsee

Name: Audio Visualization with Songsee
Author: xiaxingxiaowei1983

byxiaxingxiaowei1983

0•

数据科学与机器学习

Generates high-quality spectrograms and comprehensive audio feature-panel visualizations directly through the command line.

The songsee skill empowers Claude to perform advanced audio analysis and visualization by leveraging the songsee CLI. It allows users to generate visual representations of audio files, including mel-spectrograms, chromagrams, and HPSS, which are essential for music information retrieval (MIR) and audio engineering tasks. Whether you are debugging audio processing pipelines, analyzing specific track segments for data science, or creating visual assets for music research, this skill provides a streamlined interface for transforming sound data into detailed graphical insights.

主要功能

010 GitHub stars

02Generate multi-panel visualizations including mel, chroma, and MFCC

03Produce high-resolution spectrograms for deep audio analysis

04Support for multiple output formats including PNG and JPG

05Customizable visual styles including Magma, Inferno, and Viridis palettes

06Extract and visualize specific time slices from long audio files

使用场景

01Visualizing audio features for machine learning model training and dataset preprocessing

02Analyzing audio frequency content for music production or acoustic research

03Generating visual representations of specific audio segments for technical documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add xiaxingxiaowei1983/ai songsee

For use in Claude.ai and ChatGPT