E2 TTS
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
- Microsoft
- Organisation type
- Industry
- Country
- United States of America
- Published
- 12 September 2024
- Authors
- Sefik Emre Eskimez, Xiaofei Wang, Manthan Thakker, Canrun Li, Chung-Hsien Tsai, Zhen Xiao, Hemin Yang, Zirun Zhu, Min Tang, Xu Tan, Yanqing Liu, Sheng Zhao, Naoyuki Kanda
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Text-to-speech (TTS), 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.
- Parameters
- 335M
- Training data
- 245,760,000,000 tokens
"The architecture incorporated U-Net [23] style skip connections, 24 layers, 16 attention heads, an embedding dimension of 1024, a linear layer dimension of 4096. The character embedding vocabulary size was 399.5 The total number of parameters amounted to 335 million"
"We utilized the Libriheavy dataset [30] to train our models. The Libriheavy dataset comprises 50,000 hours of read English speech from 6,736 speakers, accompanied by transcriptions that preserve case and punctuation marks." "We also used a proprietary 200,000 hours of training data to investigate the scalability of the E2 TTS model." "All models were trained for 800,000 mini-batch updates with an effective mini-batch size of 307,200 audio frames." Token count estimate: 307,200 × 800,000 = 2…
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 4.9 × 10²⁰ FLOP
- How it was established
- Operation counting
6 FLOP / token / parameter * 245760000000 tokens * 335000000 parameters = 4.939776e+20 FLOP
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
- E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
- Last updated
- 28 November 2025
What the numbers mean
About this model
E2 TTS was published by Microsoft, in the country recorded as United States of America, during September 2024. The publishing organisation is categorised as industry.
It works in the domain of Speech, and is recorded as performing the task of text-to-speech (TTS), Speech synthesis.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
Training it took a computation budget of roughly 4.9 × 10²⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 245,760,000,000 tokens of text.
Answers
E2 TTS — common questions
E2 TTS— when was it released?
It was published in September 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
E2 TTS— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of text-to-speech (TTS), Speech synthesis. These are the areas it was designed around; they describe intent rather than a hard boundary.
E2 TTS— how much compute was used to train it?
Training consumed around 4.9 × 10²⁰ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
E2 TTS— what GPU do I need to run it?
None. This 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.
E2 TTS— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
E2 TTS— how many parameters does it have?
It has a parameter count of 335M. "The architecture incorporated U-Net [23] style skip connections, 24 layers, 16 attention heads, an embedding dimension of 1024, a linear layer dimension of 4096. The character embedding vocabulary size was 399.5 The total number of parameters amounted to 335 million". 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.
E2 TTS— who created it?
It was published by Microsoft, based in United States of America, an organisation categorised as industry.
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.