src/audio/SKILL.md
GNN audio generation and sonification. Use when creating audio representations of GNN models, generating sonification of state spaces, or working with SAPF and Pedalboard audio backends.
npx skillsauth add activeinferenceinstitute/generalizednotationnotation gnn-audio-generationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generates audio representations (sonification) of GNN models, mapping model structures, state transitions, and matrix values to sound parameters using SAPF, Pedalboard, and other audio backends.
# Run audio generation
python src/15_audio.py --target-dir input/gnn_files --output-dir output --verbose
# As part of pipeline
python src/main.py --only-steps 15 --verbose
from audio import (
AudioGenerator, process_audio, generate_audio_from_gnn,
create_sonification, analyze_audio_characteristics,
SAPFGNNProcessor, SyntheticAudioGenerator,
check_audio_backends, generate_oscillator_audio,
apply_envelope, mix_audio_channels,
convert_gnn_to_sapf, generate_audio_from_sapf
)
# Process audio step (used by pipeline)
process_audio(target_dir, output_dir, verbose=True)
# Generate audio from GNN model
result = generate_audio_from_gnn(gnn_content, output_dir="output/")
# Create sonification
audio_data = create_sonification(model_data)
# Use AudioGenerator class
gen = AudioGenerator()
# Convert GNN to SAPF format and generate audio
sapf_code = convert_gnn_to_sapf(gnn_content)
generate_audio_from_sapf(sapf_code, output_path="model.wav")
# Check available backends
backends = check_audio_backends()
# Returns: {'librosa': {'available': True}, 'soundfile': {...}, 'pedalboard': {...}}
AudioGenerator / SAPFGNNProcessor — audio generator classesprocess_audio / generate_audio_from_gnn — main generation functionscreate_sonification — sonification from model dataSyntheticAudioGenerator — procedural audio generationgenerate_oscillator_audio, apply_envelope, mix_audio_channels — low-level audiocheck_audio_backends — check librosa/soundfile/pedalboard availability# Audio generation deps
uv sync --extra audio
# Includes: librosa, soundfile, pedalboard, pydub
output/15_audio_output/This module registers tools with the GNN MCP server (see mcp.py):
process_audiocheck_audio_backendsget_audio_generation_optionsdevelopment
GNN static HTML website generation from pipeline artifacts. Use when generating browsable documentation websites, creating HTML galleries of model visualizations, or publishing pipeline results as a static site.
data-ai
GNN graph and matrix visualization generation. Use when creating network graph plots, matrix heatmaps, state space diagrams, or other visual representations of GNN models.
testing
GNN advanced validation and consistency checking. Use when performing deep validation of GNN models, checking cross-model consistency, verifying structural integrity, or running validation reports.
tools
GNN shared utility functions and helper modules. Use when working with common pipeline utilities, logging helpers, file I/O wrappers, path management, or pipeline template infrastructure.