Blog

Announcing Audiogen Codec

A low compression 48khz stereo neural audio codec for general audio, optimizing for audio fidelity.

February 20, 2024

Authors

Audiogen Team

Audiogen Codec (agc)

We are announcing the open source release of Audiogen Codec (agc). A low compression 48khz stereo neural audio codec for general audio, optimizing for audio fidelity.

It comes in two flavors:

  • agc-continuous - KL regularized, 32 channels, 100hz.
  • agc-discrete - 24 stages of residual vector quantization, 50hz.

AGC is a convolutional autoencoder based on the DAC architecture, which holds SOTA. We found that training with EMA and adding a perceptual loss term with CLAP features improved performance. These codecs, being low compression, outperform Meta's EnCodec and DAC on general audio as validated from internal blind ELO games.

Internal Blind Codec Evaluation

We trained (relatively) very low compression codecs in the pursuit of solving a core issue regarding general music and audio generation, low acoustic quality and audible artifacts, which hinder industry use for these models.

Our hope is to encourage researchers to build hierarchical generative audio models that can efficiently use high sequence length representations without sacrificing semantic abilities.

This codec will power Audiogen's upcoming models. Stay tuned! 🚀

Github Repo