A 64-spoke voice ring that listens to your mic's level, sweeps while thinking and beats while speaking, with a transcript that arrives word by word, mute and a footer that says what the mic is doing.
pnpm dlx shadcn@latest add @beautiful-ui-pro/voice-nodeNeeds your registry key. Your components.json style picks the Base UI or Radix build: radix-*, new-york and default get Radix, base-* gets Base UI.
The CLI adds the styles to the CSS file named in components.json (tailwind.css). Check that it points at your global stylesheet, that the project uses Tailwind CSS v4, and that the file is imported in your root layout. Installed by hand: paste styles.css into that file.
Import it and pass your content. The props that matter most are listed next.
"use client";
import * as React from "react";
import { VoiceNode, type VoiceState } from "@/components/ui/notchset/voice-node";
/** Wire state and transcript to your voice agent; the node handles the mic level, mute and the ring. */
export function VoiceAgent({ connect }: { connect: (handlers: { onState: (s: VoiceState) => void; onUser: (t: string) => void; onAgent: (t: string) => void }) => () => void }) {
const [state, setState] = React.useState<VoiceState>("ready");
const [heard, setHeard] = React.useState("");
const [reply, setReply] = React.useState("");
const stop = React.useRef<(() => void) | null>(null);
return (
<VoiceNode
state={state}
user={heard}
agent={reply}
onStart={() => {
setHeard("");
setReply("");
stop.current = connect({ onState: setState, onUser: setHeard, onAgent: setReply });
}}
onEnd={() => {
stop.current?.();
setState("ready");
}}
/>
);
}state–
'ready' | 'listen' | 'think' | 'speak'Your agent's phase.
user / agent–
stringTranscript so far; new words animate in.
onStart / onEnd / mic–
() => void / () => void / booleanSession control; mic level on by default.
components/ui/notchset/voice-node.tsx
This component is included with Pro.
Try the live preview above. Get Pro to install the source.