songsee-hardenedGenerate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Install via ClawdBot CLI:
clawdbot install snazar-faberlens/songsee-hardenedInstall songsee (brew):
brew install steipete/tap/songseeRequires:
Grade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://share.example.com/uploadCalls external URL not in known-safe list
https://github.com/steipete/songseeAudited Apr 24, 2026 · audit v1.0
Generated Jul 19, 2026
Musicians and producers analyze tracks by generating spectrograms and multi-panel feature visualizations (mel, chroma, HPSS) to inspect frequency content, harmonic structure, and loudness, aiding in mixing and mastering decisions.
Forensic experts examine audio recordings for tampering or deepfakes by visualizing spectrograms and feature panels to detect anomalies in frequency patterns, noise floors, or temporal inconsistencies.
Researchers studying animal sounds (e.g., bird calls, whale songs) use time-slice spectrograms to isolate and analyze specific segments, identifying species and behavioral patterns.
Educators teaching music theory or audio processing generate visual aids like chroma and MFCC plots to illustrate concepts such as pitch, timbre, and rhythm to students with hearing impairments.
Podcast engineers use loudness and spectrogram visualizations to ensure consistent audio levels, remove artifacts, and verify compliance with loudness standards (e.g., LUFS).
Offer a free basic version for spectrogram generation with limited options, and a paid pro version with advanced features like batch processing, high-resolution output, and export to cloud storage.
Wrap the songsee CLI as a cloud API that accepts audio files and returns spectrogram images or JSON feature data, charging per request or via monthly subscription for developers and businesses.
Develop a plugin for DAWs like Ableton Live or Audacity that integrates songsee visualizations directly into the editing timeline, sold as a paid add-on for professional audio engineers.
💬 Integration Tip
To integrate into automated pipelines, pipe audio directly via stdin (e.g., `cat input.wav | songsee - --format png -o output.png`) and use the `--start`/`--duration` flags to process segments without temporary files.
Scored Jun 3, 2026
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg editing.
Generate and stitch short videos via Google Veo 3.x using the Gemini API (google-genai). Use when you need to create video clips from prompts (ads, UGC-style clips, product demos) and want a reproducible CLI workflow (generate, poll, download MP4, optionally stitch multiple segments).
Generate videos using OpenAI's Sora API. Use when the user asks to generate, create, or make videos from text prompts or reference images. Supports image-to-video generation with automatic resizing.
Morfeo Academy's Remotion video style guide. Use when creating Remotion videos, stories, or animations for Paul/Morfeo Academy. Triggers on "estilo Morfeo", "mi estilo Remotion", "video para Morfeo", "story estilo Morfeo", or any Remotion video request from Paul.
Recreate low-budget AI video ad workflows using Nano Banana image generation plus Kling 3.0 video synthesis with dialogue, including prompt design, scene planning, cost control, and export handoff. Use when a user wants to produce a cinematic ad quickly (often in a few hours) with a small credit budget, or asks for a Deon-style Nano Banana + Kling pipeline.
Create AI videos with Sora 2, Veo 3, Seedance, Runway, and modern APIs using reliable prompt and rendering workflows.