# facebookresearch/audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Repository: https://github.com/facebookresearch/audiocraft
Canonical: https://ross.abutalabs.com/products/audiocraft
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-03-03T21:50:32+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 70, release rhythm 35, longevity 84
- inputs: {"age_days": 1182, "days_push": 183, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 23586, forks 2688 (observed 2026-08-28T04:11:35.106990+00:00)

## What it is
A PyTorch library from Meta for audio processing and generation with deep learning, featuring the EnCodec neural audio codec and generative models like MusicGen, AudioGen, MAGNeT, and JASCO. It includes both inference and training code for state-of-the-art text-to-music and text-to-sound models.

## Use cases
- generate music from a text prompt
- create sound effects from text descriptions
- compress and tokenize audio with a neural codec
- train custom audio generation models
- watermark generated audio
- condition music generation on melodies or chords

## When to choose
- you need state-of-the-art text-to-music or text-to-sound generation in Python
- you want to research or train audio generation models with PyTorch
- you need a high-fidelity neural audio codec like EnCodec

## When to avoid
- you only need simple audio playback or format conversion
- you lack a GPU and want fast real-time generation
- you need a production-ready end-user application rather than a research library

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, machine-learning, deep-learning, llm-inference, llm-training, tts
- domain: machine-learning, deep-learning, artificial-intelligence, audio
- platform: python, cross-platform
- tags: text-to-music, text-to-audio, neural-audio-codec, audio-watermarking, pytorch, generative-models, musicgen, encodec, audio, gpu

## Member repositories
- facebookresearch/audiocraft (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:35.106990+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 2026-08-29T16:56:26.478766+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/audiocraft (fetched 2026-08-28T04:11:35.106990+00:00, sha 657004ec68be)
  - registry_pypi: https://pypi.org/pypi/audiocraft/json (fetched 2026-08-29T07:54:10.520790+00:00, sha 900a8a3da133)
- Data as of 2026-08-30T08:39:29.467469+00:00.