Describe an instrument and play it

The challenge

Generative audio returns a file nobody can edit; a synthesizer returns a wall of knobs and one paradigm.

The scenario

A producer wants a sound that does not exist — glass resonating underwater with a breathing analog texture — and wants to keep changing it after the first note.

What goes in

A description

The sound in words: material, character, motion, how it should respond to playing.

What you can ask

Illustrative prompts. Results depend on your own data and are not deterministic.

• “Create a warm evolving synth that sounds like glass resonating underwater, with a slowly breathing analog texture and expressive MPE control.”Copy
• “A bell made of liquid crystal.”Copy
• “A punchy vintage analog bass with a little grit.”Copy

How Clearception approaches it

How the work is structured. Each step shows what its output is grounded in.

1. 1

   Read the intent

   AI-inferred

   Archetype, material and quality words become Sound DNA, each with the word that moved it.

2. 2

   Choose the engines

   Recommendation

   Modal for glass, analog for vintage drift, wavetable for movement — with a reason per engine.

3. 3

   Compile and play

   Observed

   The genome is derived deterministically and loaded into the browser engine.

What you get

The shape of what comes back — not a promised result.

• A playable patch

  DNA, strategy, genome and DSP graph — every value inspectable.

Why it matters

Editable from the first note

The result is a recipe, so there is always a next instruction.

Reasons, not magic

Each engine in the mix says why it is there.