{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/jukebox-a-generative-model-for-music-1","title":"Jukebox: A Generative Model for Music","arxiv_id":"2005.00341","date":"2020-04-30","proceeding":"Preprint 2020 4","authors":["Prafulla Dhariwal","Heewoo Jun","Christine Payne","Jong Wook Kim","Alec Radford","Ilya Sutskever"],"abstract":"We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive Transformers. We show that the combined model at scale can generate high-fidelity and diverse songs with coherence up to multiple minutes. We can condition on artist and genre to steer the musical and vocal style, and on unaligned lyrics to make the singing more controllable. We are releasing thousands of non cherry-picked samples at https://jukebox.openai.com, along with model weights and code at https://github.com/openai/jukebox","url_abs":"https://arxiv.org/abs/2005.00341v1","url_pdf":"https://arxiv.org/pdf/2005.00341v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/openai/jukebox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/Broccaloo/Jukebox_mod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/Deskaunedsei1983/jukebox-openai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/dortenenboim314/cyclic-jukebox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/elsalmi/qiskit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/inzva/music-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/kcrosley-leisurelabs/jukebox-reduce-log","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/picopicodragon/jukebox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/picopicodragon/jukebox_plain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/safakkbilici/Synthetic-Music-Generation-with-Deep-Neural-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/tdunity/fixedjukebox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"jukebox-a-generative-model-for-music-1","repo_url":"https://github.com/wzaielamri/unmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"jukebox","method_name":"Jukebox"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"vq-vae","method_name":"VQ-VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.00341","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}