PRODUCTS
SOLUTIONS
COMPANY
Neuphonic © 2026
GET IN TOUCH
GET IN TOUCH
Have something in mind? Let’s make it happen.
Have something in mind? Let’s make it happen.
ENTERPRISE
PRODUCTS
COMPANY
Neuphonic © 2026
AI VOICES THAT LIVE
ON YOUR DEVICE
AI VOICES THAT LIVE
ON YOUR DEVICE
AI VOICES THAT LIVE
ON YOUR DEVICE
Upsampling
Upsamples from 16kHz to 24kHz
Low bit-rate compression
A speech codec that compresses and reconstructs audio with near-inaudible reconstruction loss
Commercial use
Commercial use permitted
Datasets
Released with large pre-encoded datasets.
Compressed Emilia-YODAS from 1.7TB to 41GB
Key Features
Key Features
Datasets
Datasets
Released with large pre-encoded datasets.
Compressed Emilia-YODAS from 1.7TB to 41GB
Released with large pre-encoded datasets.
Compressed Emilia-YODAS from 1.7TB to 41GB
Commercial use
Commercial use
Commercial use permitted
Commercial use permitted
Low bit-rate compression
Low bit-rate compression
A speech codec that compresses and reconstructs audio with near-inaudible reconstruction loss
A speech codec that compresses and reconstructs audio with near-inaudible reconstruction loss
Upsampling
Upsampling
Upsamples from 16kHz to 24kHz
Upsamples from 16kHz to 24kHz
NeuCodec is a lightweight neural codec that encodes audio at just 0.8 kbps. Perfect for researchers and builders who need something that just works for training high quality text-to-speech models.
NeuCodec is a lightweight neural codec that encodes audio at just 0.8 kbps. Perfect for researchers and builders who need something that just works for training high quality text-to-speech models.
NeuCodec is a lightweight neural codec that encodes audio at just 0.8 kbps. Perfect for researchers and builders who need something that just works for training high quality text-to-speech models.
OUR CODEC
Key Features
OUR LATEST MODELS
OUR LATEST MODELS
OUR LATEST MODELS
Neuphonic brings super-realistic, human-like speech to any device. Private and secure. Faster and cheaper.
Neuphonic brings super-realistic, human-like speech to any device.
Private and secure. Faster and cheaper.
Neuphonic brings super-realistic, human-like speech to any device.
Private and secure.
Faster and cheaper.
PARTNERING WITH
PARTNERING WITH
PARTNERING WITH
Neuphonic brings super-realistic, human-like speech to any device.
Private and secure. Faster and cheaper.
Open source speech language models that run locally and privately.
No GPU needed. Text-to-speech and ultra-fast voice cloning.
Open source speech language models that run locally and privately. No GPU needed.
Text-to-speech and ultra-fast voice cloning.
Open source speech language models that run locally and privately.
No GPU needed.
Text-to-speech and ultra-fast voice cloning.
Products
Solutions
Company
Products
Solutions
Company
ENTERPRISE
PRODUCTS
COMPANY
Neuphonic © 2026