MusicLM is an experimental text-to-music model that can generate unique songs based on your ideas or descriptions. It is currently in beta and only available to a limited number of users. To get started, you can sign up for the waitlist on the Google AI Test Kitchen website. Once you are approved, you will be able to access MusicLM through the web, Android, or iOS.
MusicLM does not require any special hardware. You can use it on any device that has a web browser or the Google AI Test Kitchen app.
To use MusicLM, simply type in a prompt like “soulful jazz for a dinner party” and MusicLM will create two versions of the song for you. You can listen to both and give a trophy to the track that you like better, which will help improve the model.
MusicLM is still under development, but it has the potential to be a powerful tool for musicians and creatives. It can be used to generate new ideas, experiment with different styles, and create unique pieces of music.
Here are some examples of the types of music that MusicLM can generate:
- A fast-paced, upbeat song with a catchy electric guitar riff.
- A fusion of reggaeton and electronic dance music, with a spacey, otherworldly sound.
- The main soundtrack of an arcade game. It is fast-paced and upbeat, with a catchy electric guitar riff. The music is repetitive and easy to remember, but with unexpected sounds, like cymbal crashes or drum rolls.
MusicLM is a powerful tool that can be used to create unique and interesting music. If you are a musician or creative, I encourage you to try it out.
Here are the steps on how to use MusicLM:
- Go to the Google AI Test Kitchen website.
- Sign in with your Google account.
- Click on the “MusicLM” tab.
- Type in a prompt for your song.
- Click on the “Generate” button.
- Listen to the two generated songs.
- Give a trophy to the song that you like better.
- Repeat steps 4-7 until you are satisfied with the generated song.
Sources
1. blog.google/technology/ai/musiclm-google-ai-test-kitchen/
2. google-research.github.io/seanet/musiclm/examples/