descriptinc/descript-audio-codec
A neural audio codec using residual vector quantization GANs (RVQGAN) to compress 44.1 kHz audio 90x at 8 kbps while maintaining high fidelity.
Not currently ranked — collecting fresh signals.
star history
This repository provides training and inference code for Descript Audio Codec, a high-fidelity general neural audio codec. It uses residual vector quantization with a GAN-based architecture to achieve state-of-the-art compression ratios. The model operates at 44.1 kHz and supports mono/stereo audio, and serves as a universal model working across speech, music, and environment sound domains. It is designed as a drop-in replacement for EnCodec in audio language modeling applications.
Frequently asked
- What is descriptinc/descript-audio-codec?
- A neural audio codec using residual vector quantization GANs (RVQGAN) to compress 44.1 kHz audio 90x at 8 kbps while maintaining high fidelity.
- Is descript-audio-codec open source?
- Yes — descriptinc/descript-audio-codec is open source, released under the MIT license.
- What language is descript-audio-codec written in?
- descriptinc/descript-audio-codec is primarily written in Python.
- How popular is descript-audio-codec?
- descriptinc/descript-audio-codec has 1.8k stars on GitHub.
- Where can I find descript-audio-codec?
- descriptinc/descript-audio-codec is on GitHub at https://github.com/descriptinc/descript-audio-codec.