Voicebox / VB-En

Closed weights Facebook AI Research 358M parameters October 2023

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
Facebook AI Research
Organisation type
Industry
Country
United States of America, France
Published
19 October 2023
Authors
Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Yossi Adi, Jay Mahadeokar, Wei-Ning Hsu

What it does

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

Domain
Speech
Task
Speech synthesis, Text-to-speech (TTS)
Numerical format
FP16

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.

Parameters
358M

Acoustic Model: 330 million parameters Duration Model: 28M for English-only model (VB-En)

Training data
tokens

"We train an English-only Voicebox on 60K hours of data and a multilingual version on 50K hours of data covering six languages (English, French, German, Spanish, Polish, and Portuguese)." "VB-En/VB-Multi audio models are trained for 500K/750K updates with an effective batch size of 240K frames" "For training efficiency, audio length is capped at 1,600 frames and chunked randomly if the length exceeds this threshold. Duration models are trained for 600K updates with an effective batch size of 6…

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Chips used
32

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

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

Record confidence
Confident

Sources

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

Reference
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
Last updated
28 November 2025

What the numbers mean

Background

Voicebox / VB-En was published by Facebook AI Research, in United States of America, in October 2023. The organisation is categorised as industry.

It works in Speech, and is recorded as doing speech synthesis, Text-to-speech (TTS).

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Answers

Voicebox / VB-En — common questions

01

Is Voicebox / VB-En open source?

No. Voicebox / VB-En has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Voicebox / VB-En have?

Voicebox / VB-En has 358M parameters. Acoustic Model: 330 million parameters Duration Model: 28M for English-only model (VB-En). That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Who created Voicebox / VB-En?

Voicebox / VB-En was published by Facebook AI Research, based in United States of America, categorised as industry.

04

When was Voicebox / VB-En released?

Voicebox / VB-En was published in October 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Voicebox / VB-En used for?

Voicebox / VB-En works in Speech, and is recorded as handling speech synthesis, Text-to-speech (TTS). These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run Voicebox / VB-En?

None. Voicebox / VB-En 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.

Source

Original publication

Record last updated 28 November 2025

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.