CONCEPTDesign Engineeringdizzy.rounakneema.in

Dizzy

Voice-to-Native-Figma UI Creation Concept
GENERATIVE UIVOICEFIGMA
// Problem

Traditional generative UI tools output flattened PNGs or uneditable code. Designers need voice-driven generation that produces native, editable Figma objects.

// Solution

An agentic architecture translating streaming speech into a semantic command buffer, generating structured design operations via Figma MCP.

// Overview

Dizzy is a product architecture concept for voice-driven UI design. Instead of generating images, it streams voice input to an agent that builds a semantic command buffer. This buffer translates intent into structured operations for the Figma MCP, allowing the system to progressively modify native Figma designs. Later commands can intelligently update earlier decisions rather than creating entirely new assets.

// Breakdown
01
Native Output

Manipulates native Figma objects via Figma MCP instead of generating images.

02
Semantic Buffer

Maintains structured design state to allow progressive and contextual modifications.

03
Workflow

JEV/Streaming Voice → Agent Intent → Design Operations → Figma MCP.

04
Vision

Expanding into an agentic product design loop integrating visual comparison and code generation.

// At a Glance
Input
Streaming Voice
Output
Figma Native
Integration
Figma MCP
State
Semantic Buffer
// Tech Stack
Voice/JEVFigma MCPSemantic BufferAgents