Introduction
Jukebox uses hierarchical VQ-VAEs and autoregressive priors to generate music and approximate vocals. It is distinct from later text-driven music platforms. Its relevance is cross-media: learning generative capacities from large collections of cultural recordings is already becoming a paradigm that extends beyond images.
View full image ↗Page 3 of the linked paper PDF, preserving its original figures and language. The source file identifies the edition; later revision or reprint dates do not replace the node’s historical date.
Prafulla Dhariwal et al.; OpenAI · original paper · Image rights remain with their respective holders; no open licence is asserted
Source · Jukebox: A Generative Model for Music ↗RESEARCH ACCOUNT
Generating raw audio, including singing, rather than only symbolic scores.
ANTI-AI ARCHIVE · Revised 2026-10-02
Method and contribution
Jukebox compresses long audio into discrete codes using a multiscale VQ-VAE and generates those codes with autoregressive transformers. The research demonstrates music and singing conditioned on artist, genre and lyrics. Released samples, code and weights make recorded sound itself, rather than only sequences of notes, an object of inspection.
Section sources: Jukebox: A Generative Model for Music
Art-historical interpretation
Artist labels become conditioning variables, placing relations between style, vocal identity and training material inside the technical interface. The capacity to produce a similar sound does not establish permission from the people concerned. Compositions, recordings and performers remain distinct objects of research.
Section sources: Jukebox: A Generative Model for Music
Sources for this account
Author or conference abstract and version record read; full proofs and experiments were not independently reproduced.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and Generating Diverse High-Fidelity Images with VQ-VAE-2.
Compare the methods, forms of control or presentation contexts of this entry and IMPF and IMPEL publish principles for fair generative-AI licensing.
Dates & version record
Date displayed for this node: 2020-04 · Historical date recorded for the source: 2020-04
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Jukebox: A Generative Model for Music
https://arxiv.org/abs/2005.00341
Current cited URL
Provenance, translation & verification
Timeline entry #112 · Historical node
Research materials & supplement references · 1
AI Art Genealogy Research Master · p. 22 · 071
Date as recorded: 2020-04
Jukebox: A Generative Model for Music ↗
Jukebox: A Generative Model for Music
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. Jukebox: A Generative Model for Music. Art-history node #112. https://salondesrefuses.cn/en/art-history/071
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.