Rhythma

Describe the state you are carrying. Rhythma turns it into a named listening session with layered tone, movement, and reflective guidance.

Layered audio Session profiles Reflective use

Session input

ready

Start with a prompt or choose a preset, then generate a named session with audio, guidance, and a waveform.

You will get

Named session Layered audio Waveform view

Tone center · Hz Texture Pattern Seconds · 3–60

Reflective listening only. Not medical advice or a clinical treatment.

Your session

Your session appears here

Describe what you are carrying — or pick an example — then generate to receive a named session with audio and guidance.

Download WAV

waveform appears after generation

Rhythma keeps the interaction compact while exposing enough structure to make each generated session legible.

A feeling or intention becomes the starting signal.

The analyzer selects a session title, tone center, pattern, brightness, and density.

The engine blends a drone, breath pulse, and shimmer layer into one WAV session.

The final surface presents guidance, audio, waveform feedback, and a short reflection.

The core engine stays Python. The Space now serves a full-width FastAPI shell with a small JSON API.

FastAPI routes, session JSON, audio file serving, and the preserved legacy Gradio builder.

Full-screen responsive interface with examples, controls, audio playback, and visual feedback.

Layered modulation renderer that creates the listening session behind each result.