songsee

Generates spectrograms and mel, chroma, MFCC visualizations from audio files.

Updated Jun 17, 2026
One-click install
npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill songsee-cxnaive
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/cxnaive/hermes-agent-llbot/tree/main/skills/media/songsee
Command: npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill songsee-cxnaive

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires go, ffmpeg.

What problem does it solve?

This Skill solves the difficulty of performing quick, visual audio analysis and debugging without needing heavy digital audio workstation software.

Core Features & Use Cases

  • Multi-faceted Visualization: Generate spectrograms, mel-scaled plots, chroma features, and more from audio files.
  • Flexible Analysis: Supports time-slicing and various color palettes for detailed inspection of audio signals.
  • Use Case: Use this tool to debug synthesis artifacts or compare audio processing pipelines by generating a multi-panel grid of spectral features from a specific segment of a track.

Quick Start

Use the songsee skill to generate a standard spectrogram from the file track.mp3 and save the output as spectrogram.png.

Frequently Asked Questions about songsee

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a spectrogram from an audio file without using heavy DAW software?

You can generate an audio spectrogram via CLI by running the songsee tool on your audio file, which quickly produces visual plots for signal processing analysis without needing a digital audio workstation.

What audio features can I visualize for technical signal processing analysis?

Audio feature visualization includes generating spectrograms, mel-scaled plots, chroma features, and MFCC from audio files to facilitate technical audio analysis and synthesis debugging.

Do I need ffmpeg to decode non-native audio formats for spectrogram generation?

You need ffmpeg installed to decode non-native audio formats, while the core spectrogram generation and audio feature visualization require the songsee Go binary.

Can I analyze a specific time segment of a track to debug synthesis artifacts?

You can debug synthesis artifacts by using time-slicing to inspect a specific segment of a track, generating a multi-panel grid of spectral features with various color palettes.

What is the best way to compare audio processing pipelines visually?

The best way to compare audio processing pipelines is generating a multi-panel grid of spectral features from a specific track segment, allowing detailed visual inspection of audio signals via CLI.