Tacotron 2

Closed weights Google,University of California (UC) Berkeley December 2017

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Google,University of California (UC) Berkeley
Organisation type
Industry,Academia
Country
United States of America
Published
19 December 2017
Authors
Jonathan Shen, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, RJ Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis, Yonghui Wu

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Speech
Task
Speech synthesis

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
2,125,888,704 tokens

"We train all models on an internal US English dataset[12], which contains 24.6 hours of speech from a single professional female speaker." 13,680 words/hour * 24.6 = 336528 words

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident
Citations
3,047

Sources

Where this record came from and when it was last checked.

Reference
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Prediction
Last updated
25 May 2026

What the numbers mean

Background

Tacotron 2 was published by Google,University of California (UC) Berkeley, in United States of America, in December 2017. The organisation is categorised as industry,Academia.

It works in Speech, and is recorded as doing speech synthesis.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

Around 2,125,888,704 tokens went into training it.

Answers

Tacotron 2 — common questions

01

How many parameters does Tacotron 2 have?

No parameter count has been published for Tacotron 2, which is why no memory or speed figure appears on this page.

02

Who created Tacotron 2?

Tacotron 2 was published by Google,University of California (UC) Berkeley, based in United States of America, categorised as industry,Academia.

03

When was Tacotron 2 released?

Tacotron 2 was published in December 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is Tacotron 2 used for?

Tacotron 2 works in Speech, and is recorded as handling speech synthesis. These are the areas it was designed around; they describe intent rather than a hard boundary.

05

What GPU do I need to run Tacotron 2?

None. Tacotron 2 is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

06

Is Tacotron 2 open source?

The licensing for Tacotron 2 was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

Source

Original publication

Record last updated 25 May 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.