A neural codec framework for training speech LMs
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.
A speech codec that compresses and reconstructs audio with near-inaudible reconstruction loss
Upsamples from 16kHz to 24kHz
Train your own SpeechLMs without needing to build your own codec
Commercial use permitted - use it in your own tools or products
Released with large pre-encoded datasets - we’ve compressed Emilia-YODAS from 1.7TB to 41GB using NeuCodec
Available on