OpenAI JukeboxOpenAI
|
||||||
Related Products
|
||||||
About
We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artistic styles. We’re releasing the model weights and code, along with a tool to explore the generated samples. Provided with genre, artist, and lyrics as input, Jukebox outputs a new music sample produced from scratch. Jukebox produces a wide range of music and singing styles and generalizes to lyrics not seen during training. All the lyrics below have been co-written by a language model and OpenAI researchers. When conditioned on lyrics seen during training, Jukebox produces songs very different from the original songs it was trained on. We provide 12 seconds of audio to condition on and Jukebox completes the rest in a specified style. We chose to work on music because we want to continue to push the boundaries of generative models. Jukebox’s autoencoder model compresses audio to a discrete space, using a quantization-based approach called VQ-VAE.
|
About
Songer is an AI-powered music creation platform that turns ideas, lyrics, themes, and genre preferences into original songs with vocals and instrumentation in under a minute. Users start by entering a song description, lyrics, or general theme, choose up to five genres or vibes, select style and mood options like genre and instruments, and then let the AI generate a complete track that can be previewed before download. It offers multiple creation paths, including a guided Song Wizard, a Generate tab for prompts and vibes, a Custom Lyrics option to add your own words, and an Instrumental mode for backing tracks. A 30–60 second preview lets you refine songs before unlocking the full downloadable version, which you can use commercially and distribute as you wish. Songer also supports tag-based control of song structure and elements to shape verses, choruses, vocals, effects, and instruments, and users can capture an artist’s style by describing musical traits rather than naming artists.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Anyone seeking a tool to generates music samples, including rudimentary voice-oriented music tracks
|
Audience
Musicians, songwriters, and creative individuals who want to quickly generate original, professional-quality music and songs from their own lyrics, descriptions, or creative ideas
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationOpenAI
Founded: 2015
United States
openai.com/blog/jukebox/
|
Company InformationSonger
Founded: 2024
songer.co
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
|
|
|