Procedural Sound Generation

Generate game sound effects using a spec-driven workflow.

pip install numpy scipy soundfile

Spec-Driven Workflow

Step 1: Create Spec

# .studio/specs/sounds/laser.spec.py
SOUND = {
    "sound": {
        "name": "laser",
        "duration": 0.25,
        "layers": [
            {"type": "fm_synth", "carrier_freq": 600, "mod_ratio": 1.5, "mod_index": 6.0},
            {"type": "noise_burst", "duration": 0.02, "amplitude": 0.3}
        ],
        "envelope": {"attack": 0.002, "decay": 0.15, "sustain": 0, "release": 0.08}
    }
}

Step 2: Run Generator

python .studio/generate.py --only sounds

See references/sound-spec-format.md for complete format.

ZX Audio Requirements

Quality Standards (Temp Tier)

Minimum requirements:

• 2-3 synthesis layers
• Proper envelope (exp decay, NOT linear)
• Filtering (lowpass sweep or static)
• Richness (harmonics or detuning)
• Normalization (0.9 peak)

Anti-patterns:

• Simple sine + linear fade
• Single oscillator, no filtering
• Instant attack (clicks)

See references/quality-standards.md for complete checklist.

Technique Selection

Recipe Library

Workflow: (1) Find closest recipe, (2) Read file, (3) Copy and customize.

nether.toml Integration

[[assets.sounds]]
id = "laser"
path = "generated/sounds/laser.wav"

let laser = rom_sound_str("laser");
play_sound(laser);

File Organization

.studio/specs/sounds/
├── laser.spec.py
└── explosion.spec.py

generated/sounds/
├── laser.wav
└── explosion.wav