Skip to main content

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

What is MusicLM? Check out Google’s text-to-music AI

MusicLM is one of Google’s experimental artificial intelligence (AI) tools that uses natural language models to interpret your instructions. But instead of chatting to you like ChatGPT, or helping you search, like Bing Chat, MusicLM is an AI that takes what you tell it and creates music based on it.

You’ll need to join the waitlist to get access, but once you’re in, you can start making music with Google’s latest AI tool.

Music LM Artist workshop with AI Test Kitchen & Google Arts & Culture Lab

What is MusicLM?

MusicLM is  a prompt-based music creation tool driven by natural language AI. It takes inputs from the user, whether that’s “humming to the tune of Queen’s Bohemian Rhapsody,” or “ambient, soft music to study to with rain in the background.” You can create genre mash-ups, multi-instrumental compositions, or human voice sounds that have never felt vocal cords before.

For every prompt you input, MusicLM makes two tracks for you to listen to. To help improve the model, Google encourages users to reward a “trophy” to the one that feels the best, or that sounds closest to what you planned with the prompt.

How do you access MusicLM?

MusicLM prompt page.
Google

At the time of writing, Google is only taking applications for MusicLM, granting permission on a case-by-case basis. It’s not clear how many people are being given access or what the criteria are, but you can register your interest to see if Google grants you permission.

To sign up for MusicLM, head to the main page, and hit the Get Started button to sign up.

How do you use MusicLM?

To use the AI, just visit the main MusicLM page, or open up MusicLM in the Google AI Test Kitchen Apps (on Play Store and App Store, respectively), then sign in to your Google account, if necessary. On the main MusicLM page, input your prompt into the prompt window and hit Enter, or press the little arrow next to the prompt field.

You can specify instruments, styles, tempos, pitches, keys — whatever you can think of. MusicLM will then give you a couple of new tracks. You can listen to them by hitting their respective play buttons, or reward them with a trophy by selecting the corresponding icon.

The only caveat is that Google has added a protective system that won’t allow MusicLM to generate music based on artists or existing songs, so you can’t do the mash-ups that have been going viral in recent months. That’s to keep Google out of murky copyright waters.

Interested in checking our more cutting-edge AI? Try making your own GPT-4 chatbot with Dante.

Jon Martindale
Jon Martindale is the Evergreen Coordinator for Computing, overseeing a team of writers addressing all the latest how to…
Watch Google DeepMind’s robotic ping-pong player take on humans
Google DeepMind's robot ping pong player takes on a human.

Demonstrations - Achieving human level competitive robot table tennis

Ping-pong seems to be the sport of choice when it comes to tech firms showcasing their robotic wares. Japanese firm Omron, for example, made headlines several years ago with its ping-pong robot that could comfortably sustain a rally with a human player, while showing off the firm’s sensor and control technology in the process.

Read more
Google strikes back with its own lightweight AI model
Google Gemini on smartphone.

Google announced Thursday that it is releasing Gemini 1.5 Flash, it's snack-sized large language model and ChatGPT-4o mini competitor, to all users regardless of their subscription level.

The company promises "across-the-board improvements" in terms of response quality and latency, as well as "especially noticeable improvements in reasoning and image understanding."

Read more
GPT-4: everything you need to know about ChatGPT’s standard AI model
A laptop opened to the ChatGPT website.

People were in awe when ChatGPT came out, impressed by its natural language abilities as an AI chatbot originally powered by the GPT-3.5 large language model. But when the highly anticipated GPT-4 large language model came out, it blew the lid off what we thought was possible with AI, with some calling it the early glimpses of AGI (artificial general intelligence).
What is GPT-4?
GPT-4 is the newest language model created by OpenAI that can generate text that is similar to human speech. It advances the technology used by ChatGPT, which was previously based on GPT-3.5 but has since been updated. GPT is the acronym for Generative Pre-trained Transformer, a deep learning technology that uses artificial neural networks to write like a human.

According to OpenAI, this next-generation language model is more advanced than ChatGPT in three key areas: creativity, visual input, and longer context. In terms of creativity, OpenAI says GPT-4 is much better at both creating and collaborating with users on creative projects. Examples of these include music, screenplays, technical writing, and even "learning a user's writing style."

Read more