A speech foundation model

that runs on CPU in real-time

GET IN TOUCH

Have something in mind? Let’s make it happen.

NeuTTS Nano

~120M

2719

54x

NeuTTS Air

~360M

1219

24x

#Params (Active)

CPU Token/s

RTF

NEUTTS COMPARISON

NEUTTS COMPARISON

#Params (Active)

CPU Token/s

RTF

24x

24x

1219

~360M

NeuTTS Air

~120M

54x

2719

NeuTTS Nano

Ultra-realistic voices

Ultra-realistic voices

Best-in-class for its size.

Produces natural human voices

Best-in-class for its size.

Produces natural human voices

On-device

On-device

Provided in GGML format.

Runs on phones, laptops,

Raspberry Pi’s & Jetson Orin Nanos

Provided in GGML format.

Runs on phones, laptops,

Raspberry Pi’s & Jetson Orin Nanos

Instant voice cloning

Instant voice cloning

Create your own speaker with

as little as 3 seconds of audio


Create your own speaker with

as little as 3 seconds of audio


Simple architecture

Simple LM + codec architecture built off a 0.5B backbone


Runs on CPU

Runs on CPU

No data connection required.

Runs on CPU in real-time


No data connection required.

Runs on CPU in real-time


Sensitive data never leaves

the device

Sensitive data never

leaves the device

Secure & private

Secure & private

KEY FEATURES

KEY FEATURES

The #1 trending model worldwide on HuggingFace.

The #1 trending model

worldwide on HuggingFace.

The #1 trending model

worldwide on HuggingFace.

GET IN TOUCH

Have something in mind?

Let’s make it happen.

A speech foundation model that runs on CPU in real-time

A speech foundation model

that runs on CPU in real-time

NEUTTS AIR

NEUTTS AIR

NEUTTS AIR

Products

Solutions

Company

Super-fast, highly realistic, on-device

TTS speech language model with instant voice cloning

Super-fast, highly realistic, on-device

TTS speech language model

with instant voice cloning

Super-fast, highly realistic, on-device

TTS speech language model

with instant voice cloning

Products

Solutions

Company