Spoken Thoughts to System Diagrams

Turn spoken design ideas into an editable system architecture diagram in real time

Problem

Developers with hand injuries or anyone who thinks out loud struggle to capture system designs quickly. Existing tools either only transcribe speech or require mouse-drag diagramming.

Solution

A voice-first architecture editor: say 'this is an API gateway into a user service and an order service, with Kafka in between' and it generates nodes and edges live. Say 'replace the order service with a queue' to modify. Export to Excalidraw/Mermaid/PNG.

Users

Developers with motor limitations, architects who think by talking, and whiteboard-style engineers in meetings.

MVP

In-browser voice input with LLM structured extraction; auto-layout and edges; voice commands to add/remove/edit nodes and edges; export to Mermaid and PNG; local history.

Revenue

Free tier plus $8/month subscription (longer recordings, more export formats, team sharing); accessibility institutional licensing.

Why now

Voice is becoming a primary input mode, and architecture diagrams are a highly structured task that LLMs can complete. An indie dev can build a focused accessibility tool with no platform dependency.