Home Projects WaveGrad
WaveGrad
Jupyter Notebook

WaveGrad

Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.

by ivanvovk · GitHub
Stars
Forks
Created
Last commit
diffusion-modelsljspeechprobabilistic-modelsBSD-3-ClauseJupyter Notebook
View on GitHub
In plain words

Generate high-quality speech from text using a vocoder model.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
WaveGrad — GitHub preview card
📈 Star history
410409
2026-07-202026-08-31
📈 Track WaveGrad

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.

WaveGrad has 409 stars on GitHub. It has been forked 52 times. WaveGrad is written mainly in Jupyter Notebook. It has been in active development since 2020. WaveGrad is available under the BSD-3-Clause license. Its main topics are diffusion-models, ljspeech, probabilistic-models, speech.

Frequently asked questions

What is WaveGrad?

Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.

Is WaveGrad open source?

WaveGrad is an open-source project. It is released under the BSD-3-Clause license.

Is WaveGrad free?

Yes. WaveGrad is free and open source — you can use, modify and self-host it.

What license does WaveGrad use?

WaveGrad is available under the BSD-3-Clause license.

What language is WaveGrad written in?

WaveGrad is written mainly in Jupyter Notebook.

🏅 Maintainer of this project?
olud.ai badge — WaveGrad

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=ivanvovk-wavegrad)](https://olud.ai/project/ivanvovk-wavegrad.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.