Music creation 2023-02-27
Jukebox icon


No ratings
Generated music and singing in diverse genres.
Generated by ChatGPT

Jukebox is an open-source neural network tool that generates music and rudimentary singing as raw audio in multiple genres and artist styles. It releases the code and model weights with an exploration tool for generated samples.

With Jukebox, users can provide input regarding genre, artist, and lyrics, and the tool outputs new music samples in response. Jukebox produces a wide range of music and singing styles and generalizes to lyrics not seen during training.

The tool can also produce music that bears no resemblance to the songs upon which it trained when conditioned on lyrics seen during training. With Jukebox, users can condition on 12 seconds of audio, and the tool completes the remainder in a specified style.Jukebox models music directly as raw audio, which is challenging because raw audio sequences are very long.

To tackle this problem, Jukebox uses an autoencoder to compress raw audio to a lower-dimensional space, which lets the tool generate audio in that compressed space and up-sample back to the raw audio space.

Jukebox is an example of pushing the boundaries of generative models and is more expressive than tools that generate music symbolically in the form of a piano roll.

It is well-suited for users interested in experimenting with AI-generated music.


Would you recommend Jukebox?

Help other people by letting them know if this AI was useful.


Feature requests

Are you looking for a specific feature that's not present in Jukebox?
Jukebox was manually vetted by our editorial team and was first featured on March 28th 2023.
Promote this AI Claim this AI

110 alternatives to Jukebox for Music creation

Pros and Cons


Generates multiple musical genres
Open-source code
Generates raw audio
Flexible user input: genre, artist, lyrics
Handles unseen lyrics
Completes music based on 12 seconds audio
Uses autoencoder for audio compression
Handles long raw audio sequences
Can produce music unrelated to training sample
Produces broad range of music styles
More expressive than symbolic music generators
Tool for exploring generated samples
Generates rudimentary singing
Can model music in artist styles
Conditions on audio for music completion
Lyric animation displays attention


Very long audio sequences
No resemblance to trained songs
Raw audio challenging
Modeling errors in music generation
No direct music-to-lyrics alignment
Extremely long-range musical dependencies
Long audio rendering time
Discernable noise in output
Limited to predominantly English lyrics
Limited to predominantly Western music genres


What is Jukebox?
How does Jukebox generate music?
How diverse is the music generated by Jukebox?
Can I provide input for the music Jukebox generates?
How does Jukebox use autoencoders for music generation?
How is Jukebox different from other music generation tools?
How can I explore the samples generated by Jukebox?
What is the audio quality of the music generated by Jukebox?
How flexible is Jukebox in music generation?
How does Jukebox handle raw audio sequences?
What are the requirements for using Jukebox?
Can I modify the music style generated by Jukebox?
How does Jukebox handle lyrics not seen during training?
Can Jukebox generate music resembling songs it was trained on?
How does Jukebox handle long audio sequences?
How does Jukebox condition on audio?
What were the challenges in developing Jukebox?
Who is the target audience for Jukebox?
Can Jukebox generate singing in addition to music?
What is unique about Jukebox’s approach to music generation?


+ D bookmark this site for future reference
+ ↑/↓ go to top/bottom
+ ←/→ sort chronologically/alphabetically
↑↓←→ navigation
Enter open selected entry in new tab
⇧ + Enter open selected entry in new tab
⇧ + ↑/↓ expand/collapse list
/ focus search
Esc remove focus from search
A-Z go to letter (when A-Z sorting is enabled)
+ submit an entry
? toggle help menu
0 AIs selected
Clear selection