Google has unveiled its AI to generate the music of any genera, provided in text form. However, Google has not made it public due to a few reasons. Google named it “musicLM”.
MusicLM provides several features. Like it can understand your shorter instruction, i.e., hum, whistle, etc., and it can also generate long-form music if clear instructions are there. Google published the melody produced against the instruction “induces the experience of being lost in space” and “the main soundtrack of an arcade game.”
Yesterday, Google published a paper on a new AI model called MusicLM.
The model generates 24 kHz music from rich captions like “A fusion of reggaeton and electronic dance music, with a spacey, otherworldly sound. Induces the experience of being lost in space.” pic.twitter.com/XPv0PEQbUh
— Product Hunt 😸 (@ProductHunt) January 27, 2023
Google also revealed in a research paper that 280,000 hours of data were used to train this program. It was said that this data is less, and a lot of training remains. Due to a lack of training and problematic melody generation, google has not made it public.
Artificial intelligence is continuously growing and overtaking many existing professions. This is not a pioneer AI music generator. Diffusion, dance Riffusion, and OpenAI’s Jukebox are already there. But they are limited to some extent and now doing very well. But this musicaLM has something more than the rest of all.
Google’s new music model MusicLM is the breakthrough of the week.
Here it is in action.
Just describe the music and it’ll generate the track: pic.twitter.com/xAhzHfGnMH
— Pete (@nonmayorpete) January 27, 2023
