MusicLM: What the future radio will sound like.

i found this awesome google music generating model.
imagine turning the radio dial and everything is actual synthized based on some keywords. only humans feeding in text prompts.
example
Example 3
0:00
/2:00
jazz song (0:00-0:15)
pop song (0:15-0:30)
rock song(0:30-0:45)
death metal song (0:45-1:00)
rap song (1:00-1:15)
string quartet with violins (1:15-1:30)
epic movie soundtrack with drums (1:30-1:45)
scottish folk song with traditional instruments (1:45-2:00)
source: https://google-research.github.io/seanet/musiclm/examples/
https://google-research.github.io/seanet/musiclm/examples/audio_samples/story_mode/example_3.wav
what its trained on
https://arxiv.org/pdf/2301.11325.pdf


How to try it for you self
Waitlist :/
https://blog.google/technology/ai/musiclm-google-ai-test-kitchen/

Author
by oran collins
github.com/wisehackermonkey