Generate spectrograms and audio feature visualizations from audio files via CLI.
npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill songsee-mlt-oss
Please help me install this Agent Skill. Skill: songsee Source: https://github.com/MLT-OSS/hermes-agent-go/tree/main/skills/media/songsee Command: npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill songsee-mlt-oss
High-intent search queries and answers about installing and using this skill.
Run songsee followed by the audio file path, for example songsee track.mp3, to render a spectrogram. Use the -o flag to set the output file and --format to choose png or jpg.
songsee supports nine visualization types: spectrogram, mel, chroma, hpss, self-similarity, loudness, tempogram, MFCC, and spectral flux. Pass them as comma-separated values to --viz to render multiple panels in a single grid image.
WAV and MP3 are decoded natively without extra tools. For other formats such as FLAC or AAC, you need ffmpeg installed so songsee can decode them.
Use the --start and --duration flags to select a time slice, for example --start 12.5 --duration 8 to visualize eight seconds beginning at 12.5 seconds. The output renders only that segment.
Yes, pipe audio data with a dash as the input, such as cat track.mp3 | songsee - --format png -o out.png. This is useful when chaining songsee into shell pipelines.
NousResearchGenerate spectrograms and audio feature visualizations from audio files.
jakubbartnikGenerate spectrograms and audio feature visualizations from audio files via CLI.
xjtulycExtract MIR features from audio and retrieve similar tracks via k-NN.
taracodlabsGenerate mel spectrograms, chromagrams, and MFCC plots from audio files using librosa.
