GET IN TOUCH

GET IN TOUCH

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

Have something in mind?

Let’s make it happen.

Train your own SpeechLMs
without needing to build your own codec

Train your own SpeechLMs
without needing to build your own codec

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.

KEY FEATURES

KEY FEATURES

001

Low bit-rate compression

002

Commercial use

003

Upsampling

004

Datasets

001

Low bit-rate compression

002

Commercial use

003

Upsampling

004

Datasets

001

Low bit-rate compression

002

Commercial use

003

Upsampling

004

Datasets

NEUCODEC

NEUCODEC

NEUCODEC

An open-source neural codec framework for training speech LMs

An open-source neural codec

framework for training speech LMs

An open-source neural codec

framework for training speech LMs

Models

Solutions

Company

Models

Solutions

Company