Home Projects ProDiff
ProDiff
Python

ProDiff

PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

by Rongjiehuang · GitHub
Stars
Forks
License
Created
Last commit
Language
diffusion-modelsspeech-synthesistext-to-speechMITPython
View on GitHub
In plain words

Generate realistic speech from text using a fast and efficient speech synthesis 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 →
ProDiff — GitHub preview card
📈 Star history
433432
2026-07-202026-08-31
📈 Track ProDiff

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

PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

ProDiff has 432 stars on GitHub. It has been forked 50 times. ProDiff is written mainly in Python. It has been in active development since 2022. ProDiff is available under the MIT license. Its main topics are diffusion-models, speech-synthesis, text-to-speech.

Frequently asked questions

What is ProDiff?

PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

Is ProDiff open source?

ProDiff is an open-source project. It is released under the MIT license.

Is ProDiff free?

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

What license does ProDiff use?

ProDiff is available under the MIT license.

What language is ProDiff written in?

ProDiff is written mainly in Python.

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

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

[![olud.ai](https://olud.ai/badge.php?tool=rongjiehuang-prodiff)](https://olud.ai/project/rongjiehuang-prodiff.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.