Skip to content
Speech SDK
Esc
↑↓navigate↵open⌘Jpreview
On this page

Getting started

Install the packages, add the Vite plugin, and speak your first sentence.

Install

Add the engines you need. Each one pulls in @kucukkanat/speech-core and @kucukkanat/speech-audio.

bun add @kucukkanat/tts @kucukkanat/stt @kucukkanat/voices   # or npm i / pnpm add
bun add @kucukkanat/speech-react                             # optional: React hooks

Configure your bundler

The models run in Web Workers that ship inside the packages. Vite, esbuild and Bun take one plugin (webpack 5, Next.js and Rspack need none; see Bundlers for each setup). With Vite:

// vite.config.ts
import { speechSdk } from "@kucukkanat/speech-core/vite";
import react from "@vitejs/plugin-react";
import { defineConfig } from "vite";

export default defineConfig({
  plugins: [react(), speechSdk({ isolation: true })],
});

Speak

import { createTTS } from "@kucukkanat/tts";

const tts = createTTS();

// Call from a click handler the first time: browsers only allow audio after a user gesture.
document.querySelector("button")?.addEventListener("click", async () => {
  await tts.speak("Hello! This voice is generated entirely inside your browser.");
});

Listen

import { createSTT } from "@kucukkanat/stt";

const stt = createSTT();
const session = stt.listen(); // loads the model on first use, then opens the microphone
session.on("update", ({ committed, partial }) => console.log(committed, partial));
setTimeout(() => session.stop(), 10_000);
console.log("Final:", (await session).text);

Browser requirements

Needs
Text-to-speech WebGPU (recent Chrome/Edge, Safari 26+). Without it, load() rejects with webgpu-required.
Speech-to-text WebGPU or WASM with Moonshine; WebGPU with Voxtral Realtime.
Microphone A secure context: HTTPS or localhost.
Cross-origin isolation Optional. Makes the WASM fallback multi-threaded.

Check up front instead of waiting for an error:

import { detectCapabilities } from "@kucukkanat/speech-core";

const caps = await detectCapabilities(); // never throws; everything is false during SSR
if (!caps.webgpu) console.warn("No WebGPU: text-to-speech won't run here.");
if (!caps.secureContext) console.warn("The microphone needs HTTPS or localhost.");

Next steps

Was this page helpful?