Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
Xenova 
posted an update 10 days ago
Post
3105
Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon!
👉 npm i kokoro-js 👈

Try it out yourself: webml-community/kokoro-web
Link to models/samples: onnx-community/Kokoro-82M-ONNX

You can get started in just a few lines of code!
import { KokoroTTS } from "kokoro-js";

const tts = await KokoroTTS.from_pretrained(
  "onnx-community/Kokoro-82M-ONNX",
  { dtype: "q8" }, // fp32, fp16, q8, q4, q4f16
);

const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text,
  { voice: "af_sky" }, // See `tts.list_voices()`
);
audio.save("audio.wav");

Huge kudos to the Kokoro TTS community, especially taylorchu for the ONNX exports and Hexgrad for the amazing project! None of this would be possible without you all! 🤗

The model is also extremely resilient to quantization. The smallest variant is only 86 MB in size (down from the original 326 MB), with no noticeable difference in audio quality! 🤯
shub1

Hi Xenova, I have a project with essentially the same goal but without using transformers.js or npm: https://github.com/Shubin123/kokorojs

The work done with transformers.js would have saved me a ton of work and headache and I will be using it in the future.

My phenomizer is still broken is it ok if i take some of your code/logic from https://github.com/hexgrad/kokoro/blob/main/kokoro.js/src/phonemize.js

I will probably just leave my project where it's at currently with any minor bug fixes and model updates if available.
If no reply I will respect that and just leave my phenomizer broken cause I dont want to pretend like I didnt look at your version. (my tokenizer is probably not up to par either).

·
Xenova

Hey! Oh that's awesome - great work! Feel free to adapt any code/logic of mine as you'd like!

sauravpanda

I am currently developing a library aimed at enabling llms inside the browser. It's essentially a wrapper for MLC and transformer.js right now but plan to add more agentic stuff like RAG etc.

To integrate transformer.js with Next.js, I had to convert it to TypeScript. I want to ensure that I properly credit you and your work, and you can check it out here: https://github.com/sauravpanda/BrowserAI.

Additionally, I noticed that the license in transformer.js appears to be incomplete and contains default values. I wanted to bring this to your attention.

I hope this is okay with you, and I truly admire all of your work!

In this post