Skip to content

CAPABILITIES

What SHE can do.

This page explains user settings, the outputs SHE provides, and the process for recalling pieces.

COMPOSED, NOT GENERATED

What Is Procedural Art?

“The idea becomes a machine that makes the art.”

Sol LeWitt, 1967

Procedural art predates trained models. In music, this appears as algorithmic composition. The composer sets rules and parameters, and the system generates results within those limits. Controlled chance produces emergent outcomes. Musically trained individuals encode the rules for SHE.

Users modify settings instead of entering text prompts. We deliver the specific libraries requested.

Customize your library. You need not supply every detail. We use your genre, mood, and length requirements to set the parameters and build a cohesive library.

The system does not copy existing music. It constructs compositions using musical grammar.

Structured Harmony Engine

Procedural composition

Music theory

The rules, written down and inspectable

Your settings

Genre, key, tempo, mood

Builds within the rules

Controlled chance, so no two pieces are alike

Audio
Editable parts
The record

The whole piece, with the reasoning behind it

Stores the reasoning: Every musical choice is written down, and any piece comes back by its ID.

Trained generative tools

AI generation

Recordings

A catalog of songs from other artists

The model

Patterns learned across the catalog; the method stays inside

Audio
Not included: Editable parts
Not included: A record

Just audio, no understanding

Stores the notes it learned: You hear the result, not the working.

ORIGINALITY

Verified Origin through Construction

Originality stems from the construction process rather than a later claim. The engine processes only original written input, and the system logs every musical choice during production.

Theory based

Each note originates from theory taxonomies. The inputs do not use recordings or trained models.

Transparent process

The taxonomies, progressions, and the route from settings to the final piece can be inspected. The engine is built to be readable.

Recall by ID

With the same SHE version, identical settings, and the same ID, the piece reproduces note for note on any machine.

Change detection

SHE replays a piece from its record and compares the outcomes. It detects changes in the engine, style settings, weights, or taxonomies.

Original taxonomies

The taxonomies are created from theory and tradition instead of being transcribed from existing tracks. The engine and its pieces begin from a clean foundation.

SETTING THE SPACE

User Parameters

Specific settings set the boundaries of the build process. Genres and profiles are calibrated to produce engine variation. SHE recognizes musical standards, genre origins, traditional instrumentation, and the rhythms and moods linked to particular styles.

Genre

The musical tradition for the piece. Each genre is manually adjusted to define rhythm, instruments, and harmonic style.

House, Jazz, Electronic, Soul, Ambient, Hip-Hop, and over 70 others

Mood

The emotional quality, like brightness, intensity, or density. Moods may be combined.

Energetic, Melancholic, Uplifting, Dark, Peaceful

Key

The primary note that anchors the composition.

Any of the 12 musical keys

Mode

The character of the piece. SHE aligns each note to the chosen mode.

All 11 modes, including Major, Minor, and Phrygian Dominant

Chords

A specific progression or one chosen by SHE to match the genre and mood. Progressions include harmonic roles.

I-V-vi-IV, ii-V-I, vi-IV-I-V

Tempo

The speed in beats per minute, determining the feel and energy.

60-200 BPM (120 BPM default)

OUTPUT COMPONENTS

Primary Records and Data

The system constructs the structure first and then renders the audio from that structure. Each piece produces an audio recording, structured metadata with MIDI mapping and musical descriptions, and a log of all musical decisions.

The descriptions and decision logs are produced directly from the structure during production to ensure accuracy.

Data packages are arranged according to specific use cases.

Audio
  • Full song or separate tracks for chords, bass, melody, drums, and pads
  • Uncompressed WAV files using standard sample rates
  • Ready for playback, production, or integration
Arrangement (MIDI)
  • Note-level instructions for each instrument
  • Resolution of 480 ticks per beat
  • Separate tracks for instrument roles, including velocity and timing data
  • Compatible with music production software
Descriptions
  • Data for key, tempo, mode, and time signature
  • Chords and harmonic rhythm for each section
  • Section markers with bar counts and energy levels
  • Instrument roles documented during the creation process
Decisions
  • A record of each musical decision and its rationale
  • Machine-readable data paired with audio for labeling
  • The progression, form, and ID needed to rebuild the piece