descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
Built on improved RVQGAN architecture, the codec uses residual vector quantization to compress 44.1 kHz audio into discrete codes at 8 kbps bitrate while maintaining perceptual fidelity across all audio domains (speech, music, environmental sound). The universal model serves as a drop-in replacement for EnCodec in audio language modeling applications like AudioLM and MusicGen, offering both CLI tools and a Python API for integration into generative audio pipelines.
1,732 stars and 453,067 monthly downloads. Used by 4 other packages. Available on PyPI.
Stars
1,732
Forks
171
Language
Python
License
MIT
Category
Last pushed
Jan 26, 2026
Monthly downloads
453,067
Commits (30d)
0
Dependencies
7
Reverse dependents
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/descriptinc/descript-audio-codec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
crlandsc/torch-log-wmse
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
KyungsuKim42/tokensynth
The official implementation of TokenSynth (ICASSP 2025)
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".