Home Projects tacotron
tacotron
Python

tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

by keithito · GitHub
Stars
Forks
License
Created
Last commit
Language
machine-learningpythonspeech-synthesisMITPython
View on GitHub
In plain words

Generate speech from text using a pre-trained model for natural-sounding audio.

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 →
tacotron — GitHub preview card
📈 Star history
3.00k2.99k
2026-07-072026-08-31
📈 Track tacotron

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

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

tacotron has 3k stars on GitHub. It has been forked 939 times. tacotron is written mainly in Python. It has been in active development since 2017. tacotron is available under the MIT license. Its main topics are machine-learning, python, speech-synthesis, tacotron.

Frequently asked questions

What is tacotron?

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

Is tacotron open source?

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

Is tacotron free?

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

What license does tacotron use?

tacotron is available under the MIT license.

What language is tacotron written in?

tacotron is written mainly in Python.

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

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

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