INTEGRATE OUR MULTILINGUAL
NEUTTS-2M INTO YOUR SYSTEM
INTEGRATE OUR MULTILINGUAL
NEUTTS-2M INTO YOUR SYSTEM
Have something in mind? Let’s make it happen.
Solutions
Resources
Neuphonic © 2026
Solutions
Resources
Neuphonic © 2026
Solutions
Resources
Neuphonic © 2026
NeuTTS-2E: Direct the emotion, not just the words.
NeuTTS-2E: Direct the emotion,
not just the words.
NeuTTS-2E: Direct the emotion, not just the words.
Our compact open-source TTS model for controllable emotion,
built to generate expressive speech locally and privately.
Our compact open-source TTS model for controllable emotion,
built to generate expressive speech locally and privately.
Our compact open-source TTS model for controllable emotion, built to generate expressive speech locally and privately.
[
KEY FEATURES
]
Built for emotional control.
Built for emotional control.
Built for
emotional control.
Choose the emotion, keep the voice, and shape how every line is performed.
Choose the emotion, keep the voice, and shape
how every line is performed.
Choose the emotion, keep the voice, and shape how every line is performed.
Feature
Specification
#Params (Active)
~125M
CPU Threads
2
Audio Generation RTF
2x
Languages
English
Emotions
Neutral, Happy, Sad, Angry, Surprised, Fearful, Disgusted
Feature
Specification
#Params (Active)
~125M
CPU Threads
2
Audio Generation RTF
2x
Languages
English
Emotions
Neutral, Happy, Sad, Angry, Surprised, Fearful, Disgusted
Feature
Specification
#Params (Active)
~125M
CPU Threads
2
Audio Generation RTF
2x
Languages
English
Emotions
Neutral, Happy, Sad, Angry, Surprised, Fearful, Disgusted
Emotionally Expressive Voices
Generate speech that carries feeling: from joy and surprise to fear, sadness, anger, and disgust.
Emotionally Expressive Voices
Generate speech that carries feeling: from joy and surprise to fear, sadness, anger, and disgust.
Emotionally Expressive Voices
A speech codec that compresses and reconstructs audio with near-inaudible reconstruction loss.
Same Voice, Different Emotion
Explore different emotional deliveries while preserving the chosen speaker.
Same Voice, Different Emotion
Explore different emotional deliveries while preserving the chosen speaker.
Open Source
Build, experiment, and customize with NeuTTS-2E under the NeuTTS Open License.
Open Source
Build, experiment, and customize with NeuTTS-2E under the NeuTTS Open License.
Small & Efficient
125M active parameters, built for real-time generation on CPU.
Small & Efficient
125M active parameters, built for real-time generation on CPU.
On-Device
Deploy in GGML across phones, laptops, Raspberry Pi, and Jetson Orin Nano.
On-Device
Deploy in GGML across phones, laptops, Raspberry Pi, and Jetson Orin Nano.
Secure & Private
Keep sensitive voice data on-device, with no cloud dependency.
Secure & Private
Keep sensitive voice data on-device, with no cloud dependency.
Try NeuTTS-2E on Hugging Face.
Try NeuTTS-2E
on Hugging Face.
Try NeuTTS-2E
on Hugging Face.
Explore its seven emotions, test different voices,
and hear expressive speech for yourself.
Explore its seven emotions, test
different voices, and hear
expressive speech for yourself.
Explore its seven emotions, test different voices, and hear expressive speech for yourself.
Bring your products to life.
Bring your products
to life.
Bring your products
to life.
Add expressive, controllable speech to agents, characters,
robotics, interactive experiences - or whatever you build next.
Add expressive, controllable speech
to agents, characters, robotics,
interactive experiences -
or whatever you build next.
Add expressive, controllable speech to agents, characters, robotics, interactive experiences - or whatever you build next.
