songsee

Generate spectrogram and audio feature visualizations from audio files.

Updated Jul 7, 2026
One-click install
npx skills add https://github.com/TitoPrausee/nexus-toti --skill songsee-titoprausee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/TitoPrausee/nexus-toti/tree/main/data/skills/media/songsee
Command: npx skills add https://github.com/TitoPrausee/nexus-toti --skill songsee-titoprausee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

songsee removes the guesswork from listening-only audio review by turning audio files into visual representations that make frequency content, timing, and structure easier to inspect.

Core Features & Use Cases

  • Spectrogram generation: Create standard, mel-scaled, and other frequency-based views for fast audio inspection.
  • Multi-panel analysis: Combine chroma, MFCC, tempogram, flux, loudness, self-similarity, and HPSS views into one output for deeper comparison.
  • Audio workflow support: Useful for music production debugging, synthesis evaluation, dataset review, and visual documentation of audio processing results.

Quick Start

Use songsee to generate a spectrogram image from your audio file and save it to the output path you choose.

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 MP3 or WAV file?

Generate spectrograms from MP3 or WAV files by processing the audio through a visual analysis tool that extracts frequency content and timing into a clear image output. It creates standard or mel-scaled views for fast audio inspection.

Can I visualize MFCC and chroma features in one panel for audio analysis?

Visualize MFCC and chroma features in one multi-panel output by combining chroma, tempogram, flux, loudness, self-similarity, and HPSS views. This consolidates audio feature visualizations for deeper comparison and music production debugging.

Do I need ffmpeg to visualize non-native audio formats?

You need ffmpeg to visualize non-native audio formats. The system requires CLI access for native decoding and uses optional ffmpeg support to process and visualize unsupported audio files for your analysis workflow.

What is the best way to debug music production audio visually?

Debug music production audio visually by generating spectrogram and audio feature visualizations that turn listening-only review into clear visual representations. It makes frequency content, timing, and structure easier to inspect.

Can I configure time slicing and output settings for audio spectrograms?

You can configure time slicing, panels, and output settings for audio spectrograms. The tool processes decoded audio formats with configurable parameters to generate tailored visual documentation of audio processing results.

How does mel-scaled spectrogram analysis help with dataset review?

Mel-scaled spectrogram analysis helps with dataset review by transforming audio files into visual representations of frequency content. It removes guesswork from listening-only review, making dataset structure and audio features easier to inspect.