jukebox

Code for the paper "Jukebox: A Generative Model for Music"

View on GitHub↗Upstream openai/jukebox↗

Builder

OpenAI

openai • ai-lab

Stars

8,041

Using upstream star count

Forks

1,460

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Apr 29, 2020

Project creation date

README Summary

Jukebox is a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. The model uses a hierarchical VQ-VAE architecture to compress raw audio and then uses autoregressive transformers to model the compressed representations. It can generate novel music samples conditioned on genre, artist, and lyrics.

AI Dev Skills

Unmapped

Tags

Hierarchical Vector Quantized Variational AutoencodersAutoregressive TransformersMulti-scale Audio GenerationCompressed Audio RepresentationConditional Music GenerationRaw Audio ProcessingLarge-scale Neural Audio SynthesisHierarchical Generative ModelingAttention MechanismsAutoregressive Music GenerationMusic ProductionLarge-scale Neural Audio ModelsConditional GenerationMulti-scale Audio ProcessingEntertainmentSelf-hostedMultimodal AIVector Quantized Variational Autoencoders (VQ-VAE)Artist Style Transfer for MusicTextMusic Research and ExperimentationLarge-scale Foundation ModelsAudio Compression and ReconstructionCreative IndustriesTransformer ArchitectureAI Music CompositionCreative Audio Content GenerationMedia and BroadcastingCloud ComputingRaw Audio SynthesisHierarchical Generative ModelsAudioGenerative AIAutomated Music Generation with LyricsPython

Recent Activity

Updated 1 years ago

7 Days

30 Days

90 Days

Quality

research

Quality: medium
Maturity: research

PM Skills

Product Discovery

Languages

Python100.0%

Timeline

Project created: Apr 29, 2020
Forked: Mar 14, 2026
Your last push: 1 years ago
Upstream last push: 1 years ago
Tracked since: Jun 19, 2024

Similar Repos

pgvector cosine similarity · $0

Loading…