Skip to content

Paper 034 / OpenAI

Jukebox: A Generative Model for Music

Jukebox models music as compressed audio tokens with hierarchical autoregressive Transformers conditioned on artist, genre, and optionally lyrics.

UPDATED 16 Jul 2026SOURCE-LED REVIEWRESEARCH REVIEW
01

Paper, researchers, and primary source

Major lab research / speech_and_audio

Jukebox models music as compressed audio tokens with hierarchical autoregressive Transformers conditioned on artist, genre, and optionally lyrics.

CONTRIBUTION / 01

Contribution 1

Applied discrete audio compression to long-form music generation.

CONTRIBUTION / 02

Contribution 2

Used a hierarchy of priors to model multiple temporal resolutions.

CONTRIBUTION / 03

Contribution 3

Generated singing and recognizable musical structure directly in the audio domain.

02

Research context

speech_and_audio / 2020

Jukebox: A Generative Model for Music places jukebox inside the broader speech and audio discussion at OpenAI, with music generation supplying a second analytical lens. Its contribution chain has three links: Applied discrete audio compression to long-form music generation; Used a hierarchy of priors to model multiple temporal resolutions; and Generated singing and recognizable musical structure directly in the audio domain. This framing makes audio tokens a property to inspect within the study, not a label that settles later deployments. Its builder-facing implication is that hierarchical tokenization makes long audio generation feasible, though generation remains compute-heavy and controllability is imperfect.

03

Methods and evidence reading

1 cataloged method notes

METHOD / 01

Method 1

The experimental design in Jukebox: A Generative Model for Music tests applied discrete audio compression to long-form music generation and used a hierarchy of priors to model multiple temporal resolutions against the paper's documented baselines, datasets, model variants, or systems workloads.

How to read the evidence

A careful reading of Jukebox: A Generative Model for Music starts with the experiment's declared scope, not the reputation of OpenAI. The editorial method record pairs two moves: Applied discrete audio compression to long-form music generation; and Used a hierarchy of priors to model multiple temporal resolutions. The outcome-facing contribution is: Generated singing and recognizable musical structure directly in the audio domain. This supports the bounded implication that hierarchical tokenization makes long audio generation feasible, though generation remains compute-heavy and controllability is imperfect. It does not remove the source limit that the jukebox comparison in Jukebox: A Generative Model for Music is interpretable only alongside compute budget, evaluation protocol, architecture choices, task distribution, comparison baselines, and documented data, which limits claims about unseen deployments. Follow-on evaluation should therefore vary music generation while retaining an explicit jukebox baseline. To retest Jukebox: A Generative Model for Music, hold the jukebox baseline visible while changing music generation, then log where Used a hierarchy of priors to model multiple temporal resolutions no longer predicts the reported outcome.

04

Findings in the source record

1 paper-specific findings

  1. The reported evidence in Jukebox: A Generative Model for Music supports generated singing and recognizable musical structure directly in the audio domain.
05

Practical implication for AI builders

OpenAI / 2020

06

Proposed BrokenGPT application

Research blueprint / proposed status

INTEGRATION POINT / 01

Proposed route placement / jukebox

For a proposed BrokenGPT experiment based on Jukebox: A Generative Model for Music, treat long-form audio generation as an asynchronous job with provenance, rights metadata, progress stages, and preview checkpoints. Keep the jukebox path isolated, versioned, and attributable to this research record.

VALIDATION METRIC / 02

Proposed acceptance test / music generation

Validate the proposed jukebox route against the paper's reported outcome: Generated singing and recognizable musical structure directly in the audio domain. Measure transcription or generation quality, language slices, and acoustic robustness for the Jukebox: A Generative Model for Music candidate, then isolate music generation regressions before judging the proposed jukebox route.

TRADEOFF / 03

Proposed decision boundary / audio tokens

Balance fidelity, latency, and uneven domain coverage before promoting the proposed audio tokens design. Because A production test of jukebox must also examine new hardware, a later model revision, changed operating conditions, another user population, and a different product, none of which the reported music generation result resolves automatically, adoption remains conditional on replay under BrokenGPT's selected model, runtime, and policy configuration.

07

Limitations, verification, and source

Boundaries recorded with the paper

Limitations

  • The jukebox comparison in Jukebox: A Generative Model for Music is interpretable only alongside compute budget, evaluation protocol, architecture choices, task distribution, comparison baselines, and documented data, which limits claims about unseen deployments.
  • A production test of jukebox must also examine new hardware, a later model revision, changed operating conditions, another user population, and a different product, none of which the reported music generation result resolves automatically.

PRIMARY SOURCES

  1. 01
    Jukebox: A Generative Model for Music

    OpenAI — Primary primary arXiv paper / 30 April 2020 / Prafulla Dhariwal, Heewoo Jun, Christine Payne, and 3 more

Related research reviews

View all 100 credited research papers

STRAIGHT ANSWERS

Frequently asked questions

01What does Jukebox: A Generative Model for Music study?

Jukebox models music as compressed audio tokens with hierarchical autoregressive Transformers conditioned on artist, genre, and optionally lyrics.

02Which methods does Jukebox: A Generative Model for Music use?

The experimental design in Jukebox: A Generative Model for Music tests applied discrete audio compression to long-form music generation and used a hierarchy of priors to model multiple temporal resolutions against the paper's documented baselines, datasets, model variants, or systems workloads.

03What does Jukebox: A Generative Model for Music report?

The reported evidence in Jukebox: A Generative Model for Music supports generated singing and recognizable musical structure directly in the audio domain.

04What is the proposed BrokenGPT application for Jukebox: A Generative Model for Music?

Proposed: treat long-form audio generation as an asynchronous job with provenance, rights metadata, progress stages, and preview checkpoints.

MAJOR LAB RESEARCH / PAPER 034

Continue after Jukebox: A Generative Model for Music

After Jukebox: A Generative Model for Music, browse the full index for adjacent speech_and_audio research and work from OpenAI.

Open the paper index