INTEGRATE OUR EXPRESSIVE
NEUTTS-2E INTO YOUR SYSTEM
INTEGRATE OUR EXPRESSIVE
NEUTTS-2E INTO YOUR SYSTEM
Have something in mind? Let’s make it happen.
SOLUTIONS
COMPANY
Neuphonic © 2026
SOLUTIONS
COMPANY
Neuphonic © 2026
SOLUTIONS
COMPANY
Neuphonic © 2026
Voices with real emotion.
Our most expressive on-device TTS model yet.
Voices with real emotion.
Our most expressive on-device TTS model yet.
Voices with real emotion.
Our most expressive on-device TTS model yet.
INTEGRATE OUR MULTILINGUAL
NEUTTS-2M INTO YOUR SYSTEM
Have something in mind?
Let’s make it happen.
Models
Solutions
Company
On-device TTS with highly realistic speech, real-time emotional control, and expressive delivery across a range of selection.
On-device TTS with highly realistic speech, real-time emotional control,
and expressive delivery across a range of selection.
Super-fast, highly realistic, on-device TTS speech language model with instant voice cloning
KEY FEATURES
001
Emotionally expressive voices
002
On-device
003
Simple architecture
004
Secure & private
005
Runs on CPU
001
Emotionally expressive voices
002
On-device
003
Simple architecture
004
Secure & private
005
Runs on CPU
Ultra-realistic voices
Best-in-class for its size.
Produces natural human voices
On-device
Provided in GGML format.
Runs on phones, laptops,
Raspberry Pi & Jetson Orin Nano
Instant voice cloning
Create your own speaker with
as little as 3 seconds of audio
Simple architecture
Simple LM + codec architecture built off a 0.2B backbone
Runs on CPU
No data connection required.
Runs on CPU in real-time
Sensitive data never
leaves the device
Secure & private
Feature
Specification
#Params (Active)
~125M
CPU Threads
2
Audio Generation RTF
2x
Emotions
Neutral, Happy, Sad, Angry, Surprised, Fearful, Disgusted
Languages
English
KEY FEATURES
001
Emotionally expressive voices
002
On-device
003
Simple architecture
004
Secure & private
005
Runs on CPU
001
Emotionally expressive voices
002
On-device
003
Simple architecture
004
Secure & private
005
Runs on CPU
001
Emotionally expressive voices
002
On-device
003
Simple architecture
004
Secure & private
005
Runs on CPU
Feature
Specification
#Params (Active)
~125M
CPU Threads
2
Audio Generation RTF
2x
Emotions
Neutral, Happy, Sad, Angry, Surprised, Fearful, Disgusted
Languages
English
Feature
Specification
#Params (Active)
~125M
CPU Threads
2
Audio Generation RTF
2x
Emotions
Neutral, Happy, Sad, Angry, Surprised, Fearful, Disgusted
Languages
English
Models
Solutions
Company
Models
Solutions
Company