# descriptinc/descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Repository: https://github.com/descriptinc/descript-audio-codec
Canonical: https://ross.abutalabs.com/products/descript-audio-codec
Homepage: https://descript.notion.site/Descript-Audio-Codec-11389fce0ce2419891d6591a68f814d5
Language: Python
License: MIT
License Family: permissive
Topics: audio, audio-compression, compression-algorithm, deep-learning, pytorch, codec, gans, generative-adversarial-network, residual-vector-quantization
Last push: 2026-07-16T23:56:38+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 8, longevity 84
- inputs: {"age_days": 1178, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1846, forks 187 (observed 2026-08-28T04:05:43.435331+00:00)

## What it is
Descript Audio Codec (.dac) is a high-fidelity neural audio codec based on improved RVQGAN that compresses audio at roughly 90x compression (e.g., 44.1 kHz audio down to 8 kbps). It ships as a pip-installable Python package with CLI encode/decode commands and pretrained weights for 16, 24, and 44.1 kHz mono/stereo audio.

## Use cases
- compress audio files to very low bitrates with high fidelity
- encode audio into discrete codes for audio language models like AudioLM or MusicGen
- replace EnCodec as a tokenizer in generative audio pipelines
- decode .dac files back to wav audio
- preprocess speech, music, and environmental audio for machine learning

## When to choose
- you need a drop-in EnCodec replacement with better compression at 44.1 kHz
- you need discrete audio tokens for training audio generation models
- you want MIT-licensed codec weights for speech, music, and general audio

## When to avoid
- you need real-time streaming or ultra-low-latency encoding
- you need multichannel (beyond stereo) or video codecs
- you cannot run GPU/CPU inference with PyTorch dependencies

## Facets
- artifact type: library
- maturity: stable
- function: audio-processing, compression, machine-learning, deep-learning
- domain: machine-learning, media
- platform: python, cross-platform, cli
- tags: audio-codec, neural-codec, rvqgan, pytorch, audio-compression, encodec-alternative, audio

## Member repositories
- descriptinc/descript-audio-codec (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:43.435331+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:17:52.673635+00:00, confidence not recorded.
  - readme: https://github.com/descriptinc/descript-audio-codec (fetched 2026-08-28T04:05:43.435331+00:00, sha 8833e47f9d96)
  - homepage: https://descript.notion.site/Descript-Audio-Codec-11389fce0ce2419891d6591a68f814d5 (fetched 2026-08-29T10:56:58.216526+00:00, sha 73a6ba54b760)
  - registry_pypi: https://pypi.org/pypi/descript-audio-codec/json (fetched 2026-08-29T10:56:58.225594+00:00, sha 3f9ab6a83559)
- Data as of 2026-08-30T08:39:29.467469+00:00.