AI People Wiki

Builders & open source

Jade Copet

First author of MusicGen and co-first author of EnCodec, both released in Meta's AudioCraft library

Jade Copet is first author of the MusicGen paper, Simple and Controllable Music Generation, and co-first author with Alexandre Défossez of the EnCodec neural audio compression paper. Both papers list their authors at Meta AI, with EnCodec naming the FAIR team, and both models are part of Meta's AudioCraft library, which releases code under the MIT license and model weights under CC-BY-NC 4.0. Copet is also a co-author of the Code Llama paper and of the Facebook AI Research paper on generative spoken language modeling from raw audio, and Copet's GitHub profile lists the facebookresearch organization.12345678

At a glance

Current role
None confirmed in the sources
Work listed
2
Sources cited
10
Profile reviewed

Audio and speech research

Jade Copet's work at Facebook AI Research includes spoken language modeling: Copet co-authored the 2021 paper introducing Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio without text or labels.7

In 2022 Copet was co-first author, with Alexandre Défossez, of EnCodec, a neural audio codec written by the FAIR team at Meta AI, and co-authored AudioGen, a model for generating audio from text descriptions. In 2023 Copet was first author of MusicGen, "Simple and Controllable Music Generation", a single-stage language model that generates music conditioned on text or melody.34912

EnCodec and MusicGen are both part of Meta's AudioCraft library, whose repository releases code under the MIT license and model weights under CC-BY-NC 4.0.5

Code generation

Copet is a co-author of the 2023 Code Llama paper, which describes a family of open foundation models for code. In September 2025 Copet was the first individual author listed, after the FAIR CodeGen team, on the paper introducing CWM, an open-weights language model for research on code generation with world models.610

Work and contributions

  • MusicGen (AudioCraft) Open-source code

    First author, with equal contribution marked for Felix Kreuk, and a core-team member on the MusicGen paper (2023). The AudioCraft repository, which includes MusicGen, cites the paper and releases its code under the MIT license and its model weights under CC-BY-NC 4.0.125

  • EnCodec Published research

    Co-first author with Alexandre Défossez of High Fidelity Neural Audio Compression (2022), the EnCodec paper; the AudioCraft repository describes EnCodec as its audio compressor and tokenizer.345

Timeline

  1. Co-authored "Generative Spoken Language Modeling from Raw Audio" at Facebook AI Research.7
  2. Co-authored "AudioGen: Textually Guided Audio Generation".9
  3. Co-first author of the EnCodec paper, "High Fidelity Neural Audio Compression".3
  4. First author of MusicGen, "Simple and Controllable Music Generation".1
  5. Co-authored the Code Llama paper on open foundation models for code.6
  6. First individual author listed on the FAIR CodeGen team's CWM open-weights model paper.10

Documented roles

The sources do not confirm a current role; these are the roles they document.

  • Listed with Meta AI, FAIR Team on the EnCodec paper (2022) and with Meta AI on the MusicGen paper (2023), Meta AI (FAIR)428

Companies in their history

  • Meta 106 people in the wiki

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

10 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Simple and Controllable Music Generation (arXiv 2306.05284)arXiv · Paper · published Jun 8, 2023 · accessed Oct 21, 2026
  2. Simple and Controllable Music Generation — paper PDF (author affiliation: Meta AI)arXiv · Paper · published Jun 8, 2023 · accessed Oct 21, 2026
  3. High Fidelity Neural Audio Compression (arXiv 2210.13438)arXiv · Paper · published Oct 24, 2022 · accessed Oct 21, 2026
  4. High Fidelity Neural Audio Compression — paper PDF (author affiliations: Meta AI, FAIR Team)arXiv · Paper · published Oct 24, 2022 · accessed Oct 21, 2026
  5. facebookresearch/audiocraft README and license sectionMeta (GitHub repository) · Repository · accessed Oct 21, 2026
  6. Code Llama: Open Foundation Models for Code (arXiv 2308.12950)arXiv · Paper · published Aug 24, 2023 · accessed Oct 21, 2026
  7. On Generative Spoken Language Modeling from Raw Audio — paper PDF (author affiliation: Facebook AI Research)arXiv · Paper · published Feb 1, 2021 · accessed Oct 21, 2026
  8. JadeCopet (Jade Copet) on GitHubGitHub · Official page · accessed Oct 21, 2026
  9. AudioGen: Textually Guided Audio Generation (arXiv 2209.15352)arXiv · Paper · published Sep 30, 2022 · accessed Oct 21, 2026
  10. CWM: An Open-Weights LLM for Research on Code Generation with World Models (arXiv 2510.02387)arXiv · Paper · published Sep 30, 2025 · accessed Oct 21, 2026