building an app in vision pro using my voice

I felt inspired to prototype a transcription app I've been thinking about lately, starting with the user interface, using tailwind and nextjs.

But I'm in the vision pro, and not paired with my mac — I don't have a keyboard, vscode, or a terminal — how can I create it?

We’re working on a tool called rendition. Rendition creates figma designs and code for user interfaces based on text prompts.

In the vision pro, I navigated to renditioncreate.com where I can describe a UI, and rendition will create a few versions for me.

But vision pro lacks a physical keyboard by default, and the virtual keyboard... kinda sucks. I didn't want to stare at virtual keys and click my fingers together 100 times to describe my component.

Fortunately the vision pro makes voice-to-text a natural experience. I could speak the description of the UI I wanted to build in rendition.

Rendition added some nice touches, like creating an animation for streaming text, and hooked up the browser microphone api to capture my audio feed.

Leave a Comment