---
title: Introduction
description: On-device text-to-speech with voice cloning and streaming speech-to-text for the browser. Models run on WebGPU in Web Workers — no server, no API keys, nothing leaves the device.
icon: house
---

```ts
import { createSTT } from "@kucukkanat/stt";
import { createTTS } from "@kucukkanat/tts";

const tts = createTTS();
await tts.speak("Hello! I'm running entirely in your browser."); // from a click handler

const stt = createSTT();
const session = stt.listen();
session.on("update", ({ text }) => console.log(text));
```

Try it right here — the model downloads once (about 725 MB) and is cached by your browser:

<TrySpeak />

## Packages

**[@kucukkanat/tts](/speech/packages/tts)**

Voice-cloning text-to-speech (Chatterbox Turbo / Chatterbox): streaming playback, karaoke timing, clips.

**[@kucukkanat/stt](/speech/packages/stt)**

Streaming speech-to-text (Moonshine / Voxtral Realtime): microphone, files, any audio stream.

**[@kucukkanat/voices](/speech/packages/voices)**

A persistent voice library (IndexedDB) with demo voices and clip preparation.

**[@kucukkanat/speech-react](/speech/packages/react)**

React hooks: useSpeak, useTranscription, useVoices, useEngine and more.

**[@kucukkanat/speech-audio](/speech/packages/audio)**

Microphone frames, gapless player, recorder, WAV decoding and resampling.

**[@kucukkanat/speech-core](/speech/packages/core)**

The Vite plugin, typed errors, capability detection and worker RPC.

## Why on-device

- **Private**: audio and text never leave the browser.
- **Free to run**: no inference servers, no API keys, no per-minute pricing.
- **Offline after the first load**: models are cached by the browser.
- **Developer-first**: one-line happy paths, `AbortSignal` everywhere, typed errors with stable codes, and per-model
  options checked at compile time.

**[Clone a voice](/speech/guides/voice-cloning)**

Record a few seconds, then hear any text in that voice — live on the page.

**[Open the playground](/speech/playground)**

Every model and parameter, with karaoke highlighting and live dictation.
