songsee

Generate spectrograms and audio feature panels from audio files using songsee CLI.

6|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/me2Doc/friendlyclaw --skill songsee-me2doc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: songsee
Source: https://github.com/me2Doc/friendlyclaw/tree/main/body/skills/songsee
Command: npx skills add https://github.com/me2Doc/friendlyclaw --skill songsee-me2doc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires songsee.

What problem does it solve?

This Skill solves the difficulty of manually analyzing audio characteristics by providing an automated way to generate visual representations and feature panels from audio files.

Core Features & Use Cases

  • Visual Analysis: Generate high-quality spectrograms, mel-spectrograms, and chroma features from audio tracks.
  • Time-Slice Processing: Isolate specific segments of audio for targeted analysis or export.
  • Use Case: A music producer can use this to quickly visualize the frequency distribution and tempo of a track to identify mixing issues or structural patterns without opening a DAW.

Quick Start

Use the songsee skill to generate a spectrogram and mel-spectrogram visualization for the file track.mp3.

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 for frequency analysis?

To generate a spectrogram from an audio file, you need a tool that visualizes frequency distributions over time. This Skill processes various audio formats to output detailed visual spectrograms and feature panels for technical audio analysis.

Can I visualize mel-spectrograms and chroma features from MP3 tracks without a DAW?

Yes, you can visualize mel-spectrograms and chroma features from MP3 tracks without a DAW. It processes audio files directly to generate visual representations, allowing you to identify structural patterns and mixing issues quickly.

What's the best way to isolate specific time segments for targeted audio visualization?

The best way to isolate time segments for audio visualization is using time-slice processing. This feature allows you to target specific segments of an audio track for focused frequency range inspection and export.

Does the songsee CLI require ffmpeg to decode non-native audio formats?

Yes, the songsee CLI requires optional ffmpeg support to decode non-native audio formats. While the core binary handles native formats, ffmpeg integration ensures broader compatibility for analyzing various audio files.

Why use automated spectrogram visualization for music production analysis?

Automated spectrogram visualization solves the difficulty of manually analyzing audio characteristics. It provides an automated way to generate visual representations from audio files, helping music producers inspect frequency ranges and tempos efficiently.