Assembling...
Full-duplex conversational voice model enabling real-time two-way dialogue with persona-driven voice synthesis. Supports simultaneous listening and speaking with 70ms turn-switching latency, custom voice personas, and emotion-aware response generation.
Talk naturally with PersonaPlex 7B
Start a conversation and speak freely. The AI will listen and respond naturally — no buttons between messages.
Demo Mode · Voice: Browser
First open-source full-duplex conversational model at 7B scale
70ms turn-switching latency rivals human reaction time
Apache 2.0 license enables unrestricted commercial deployment
Deploy AI voice agents that handle customer inquiries with natural conversation flow and real-time responses.
Build always-on voice assistants for enterprise applications with full-duplex capabilities.
Enable voice-first healthcare consultations with HIPAA-compliant conversational AI.
Replace traditional IVR menus with natural language voice agents that understand intent.
// PersonaPlex 7B — Conversational Voice Session
import { VoiceSession } from "@arkitekton/voice";
const session = await VoiceSession.create({
model: "vm-nv-001",
vendor: "nvidia",
config: {
fullDuplex: true,
language: "en-US",
turnDetection: "server_vad",
},
});
session.on("speech_started", () => {
console.log("Agent is speaking...");
});
session.on("transcript", (text) => {
console.log("User said:", text);
});
// Connect to audio stream
const mic = await navigator.mediaDevices.getUserMedia({ audio: true });
session.connect(mic);GPU-accelerated speech AI and conversational frameworks