The Most Accurate
Real-Time Voice Platform
Yuui is a real-time voice changer powered by cloned voices. Build a voice model, switch voice output live, and stream audio with low-latency WebSocket transport. Integrate through our SDKs and REST APIs to ship voice features in your product fast.
Everything you need for AI voice
From cloning to deployment, Yuui provides the complete toolkit for creating and managing AI voices at any scale.
Most Accurate Cloning
Industry-leading voice cloning accuracy. Clone voices from short recordings and preserve timbre, prosody, and speaking style for production-quality output.
AI Voice Marketplace
Browse and discover thousands of high-quality AI voices created by our community. Find the perfect voice for your project or monetize your own creations.
Developer SDK
Integrate in minutes with TypeScript-friendly SDKs, REST endpoints, and real-time WebSocket streaming for low-latency voice transformation pipelines.
Get started in minutes
Three simple steps to clone a voice, apply real-time transformation, and deploy it in your app.
Upload Audio
Record or upload clean voice samples. Our pipeline trains a reusable cloned voice profile that can be used for live or offline synthesis.
Clone & Route
Select your cloned voice and route audio through the real-time changer. Tune parameters such as pitch, speaking rate, and expressiveness.
Deploy Anywhere
Connect with secure API keys using SDK or direct WebSocket sessions. Stream transformed audio live or generate files asynchronously.
Accuracy Rate
Latency
Voice Models
Languages
Simple pricing for every stage
Start free, scale with usage, and move to enterprise when you need dedicated infrastructure and advanced security controls.
Hobbyist / Free
$0
For prototyping and personal projects.
- Monthly free usage
- Basic voice cloning
- Developer dashboard
Pro Developer
Pay per API call
For shipping production features fast.
- Usage-based billing
- Real-time WebSocket streaming
- Priority support
Enterprise
Custom
For teams with scale, security, and SLA requirements.
- Volume discounts
- Dedicated infrastructure
- Security & compliance support
Built for developers
Our SDK is designed for production integration of real-time voice changing and cloned voice synthesis. It includes TypeScript support, streaming sessions, and server-to-server API workflows.
import { Studio } from "@yuui/sdk";
const studio = new Studio({
apiKey: process.env.YUUI_API_KEY,
});
// Clone a voice from audio
const voice = await studio.voices.clone({
name: "My Voice",
files: ["sample.mp3"],
});
// Open a low-latency streaming session
const session = await studio.stream.connect({
voiceId: voice.id,
transport: "websocket",
});
// Transform audio in real-time
await session.sendAudio(chunk);
session.on("audio", (packet) => {
play(packet.output);
});Ready to get started?
Join thousands of developers and creators using Yuui to build the next generation of voice-powered applications.