Generate spectrograms and feature-panel visuals from audio for analysis and presentation.
Based on the materials, songsee is an open-source local CLI for generating spectrogram and feature visualizations from audio, with no declared secrets or remote endpoints, so the overall risk is low. The main considerations are limited to reading local/stdin audio, writing output images, and optionally relying on local ffmpeg for some formats.
The materials explicitly state that no keys or environment variables are required, and the README does not request any API keys, account tokens, or other sensitive credentials; no clear credential leakage or abuse surface is evident.
The materials list no remote host endpoints, and the README describes only local audio processing to generate images; it does not indicate sending user audio, metadata, or outputs to external services, so no network egress is apparent.
The system marks it as prompt-only, and the documentation only shows CLI usage and flags; there is no stated capability for arbitrary code execution, starting extra system services, or expanding system privileges. The note that other formats use ffmpeg 'if available' appears to be an optional local dependency rather than an additional remote execution surface.
Per the documentation, the tool reads user-supplied local audio files or stdin and writes visualization results to local output files; this is normal local data access for its stated function, and no excessive access beyond audio input and image output is described.
The source is an open-source GitHub repository with very high community adoption (about 377k stars), and the code is in principle auditable; these are strong risk-reducing signals. The license is undeclared and maintenance status is unknown, but the current materials do not justify a higher-risk rating on that basis alone.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "songsee" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/songsee/SKILL.md 2. Save it as ~/.claude/skills/songsee/SKILL.md 3. Reload skills and tell me it's ready
Show me how to use the songsee CLI to generate a spectrogram from a local audio file named sample.wav, including common parameters and where the output file will be saved.
A set of runnable command examples with parameter explanations and a description of the generated output.
I want to use the songsee CLI to create a panel visualization for an audio clip that includes a spectrogram, energy, and other features. Give me the command, parameter suggestions, and export settings suitable for a paper figure.
A command workflow for multi-feature visualization plus export recommendations for presentation or publication.
Help me design a script that batch-runs the songsee CLI on all audio files in a folder, generates spectrograms, and saves them to an output directory using the original filenames.
A batch script or command workflow that automates generation and organization of multiple audio visualizations.
Generate spectrograms + feature panels from audio.
Quick start
songsee track.mp3songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,fluxsongsee track.mp3 --start 12.5 --duration 8 -o slice.jpgcat track.mp3 | songsee - --format png -o out.pngCommon flags
--viz list (repeatable or comma-separated)--style palette (classic, magma, inferno, viridis, gray)--width / --height output size--window / --hop FFT settings--min-freq / --max-freq frequency range--start / --duration time slice--format jpg|pngNotes
--viz renders a grid.Generate shareable code or text diffs for review and collaboration.
Automate OpenClaw nightly releases, branch maintenance, and forward-porting to main.
Debug Node.js apps with inspect, breakpoints, heap, and CPU profiling.
Audit and harden OpenClaw hosts for security and operational health.
List chats, review message history, and send iMessage or SMS from CLI.
Run Parallels smoke tests with Discord roundtrip verification across host and guest.
Search audio samples semantically and assist music production with MIDI and stems.
Extract YouTube audio and analyze tempo, mood, energy, and synced lyrics.
Generate Python unit tests with coverage comparisons and concrete edge case suggestions.
Analyze audio structure, rhythm, and key with structured JSON and visual outputs.
Get real track BPM, key, mood, and genre metadata for analysis.
Control Spotify playback, manage playlists, and generate AI playlists through MCP tools.