Google deploys Lyria 3 in Gemini app, bringing AI music generation to millions worldwide

Gemini can now generate AI music for you, no lyrics required

The American poet Henry Wadsworth Longfellow called music "the universal language of mankind." Is that still true when the so-called music is being generated by a probabilistic robot instead of a human? We're about to find out. Google has announced its latest Lyria 3 AI model is being deployed in the Gemini app, vastly expanding access to AI music generation. Google DeepMind has been tinkering with Lyria for a while now, offering limited access in developer-oriented products like Vertex AI. Lyria 3 is more capable than previous versions, and it's also quicker to use. Just select the new "Create music" option in the Gemini app or web UI to get started. You can describe what you want and even upload an image to help the robot get the right vibe. And in a few seconds, you get music (or something like it). In case there was any uncertainty about whether Lyria tracks still counted as a human artistic endeavor, worry not! Unlike past versions of the model, you don't even have to provide lyrics in your prompt. You can be vague with your request, and the model will create suitable lyrics for the 30-second song. Although with that limit, "jingle" might be more accurate. In addition to the track, each music creation job will come with an album cover-style image created by the Nano Banana model. Gemini will also have a pre-loaded set of AI tracks that you can choose to remix to your heart's content. The Lyria 3 tools are also coming to Google's Dream Track toolkit for YouTube Shorts, which will pair nicely with the Veo AI video options. So what kind of tracks can you expect Gemini to spit out? Google has provided some examples: "Sweet Like Plantain" Prompt: I'm feeling nostalgic. Create a track for my mother about the great times we had as kids and the memories of her home-cooked plantains. Make it a fun afrobeat track with a true African vibe. "Motown Parody" Prompt: Quintessential 1970s Motown soul. Lush, orchestral R&B production. Warm bassline with melodic fills, locked into a steady drum groove with crisp snare and tambourine. Vintage organ harmonic bed. Three-piece brass section. Gritty, gospel-tinged male tenor lead. "Pop Flutter" Prompt: Wistful and airy. Soft, breathy female vocals with intimacy. Rapid-fire drum and bass rhythm, low-passed and softened. Deep, warm bass swells. Dreamy electric piano chords and subtle chime textures. Rainy city vibes. "Sea Shanty" Prompt: An authentic A capella Sea Shanty featuring a robust male choir singing in a traditional call-and-response format. The piece is entirely vocal, relying on synchronized foot-stomps on a wooden deck and sharp handclaps to provide the rhythmic pulse. The lead is a weathered male baritone with a gravelly timbre who sings the narrative 'chant' lines. He is immediately answered by a powerful male choir singing in rich, rugged harmony on the 'response' lines. The voices are recorded with a natural room reverb that simulates the acoustic environment of a wooden ship's deck, giving the vocals a resonant, atmospheric quality. The performance is energetic and driving, with the choir leaning into the rhythm of the stomps to create a sense of focused, communal effort. There are no instruments, only the layered textures of collective male voices spanning tenor, baritone, and bass ranges, all contributing to a confident, monolithic sound. Sour notes AI-generated music is not a new phenomenon. Several companies offer models that ingest and homogenize human-created music, and the resulting tracks can sound remarkably "real," if a bit overproduced. Streaming services have already been inundated with phony AI artists, some of which have gathered thousands of listeners who may not even realize they're grooving to the musical equivalent of a blender set to purée. Still, you have to seek out tools like that, and Google is bringing similar capabilities to the Gemini app. As one of the most popular AI platforms, we're probably about to see a lot more AI music on the Internet. Google says tracks generated with Lyria 3 will have an audio version of Google's SynthID embedded within. That means you'll always be able to check if a piece of audio was created with Google's AI by uploading it to Gemini, similar to the way you can check images and videos for SynthID tags. Google also says it has sought to create a music AI that respects copyright and partner agreements. If you name a specific artist in your prompt, Gemini won't attempt to copy that artist's sound. Instead, it's trained to take that as "broad creative inspiration." Although it also notes this process is not foolproof, and some of that original expression might imitate an artist too much. In those cases, Google invites users to report such shared content. Lyria 3 is going live in the Gemini web interface today and should be available in the mobile app within a few days. It works in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, but Google plans to add more languages soon. While all users will have some access to music generation, those with AI Pro and AI Ultra subscriptions will have higher usage limits, but the specifics are unclear.

Google adds music generation capabilities to the Gemini app

Google announced on Wednesday that it's adding a music generation feature to the Gemini app. The company is using DeepMind's Lyria 3 music generation model to power the feature, which is still in beta. To use the feature, you'll describe the song you want to create, and the app will generate a track along with lyrics. For instance, you could ask Gemini to create a "comical R&B slow jam about a sock finding its match," and the app will generate a 30-second track along with a cover art made by Nano Banana. Google said that you can even upload a photo or a video, and the AI-powered tool will create a song to match the mood of the media file. The company said that Lyria 3 improves on the previous generation of models, creating more realistic and complex music tracks. Users can also change and control other elements like style, vocals, and tempo. Along with rolling out Lyria 3 to the Gemini app, Google is making the model available to YouTube creators through the Dream Track feature on YouTube, a tool that helps creators make AI-generated tracks. The option was only available to YouTube creators in the U.S. until now. But with this release, Google is expanding Dream Track availability globally. Google said that you can't mimic an artist outright, but if you add an artist's name to your prompt, Gemini will create a track in a similar style or a mood. (It's not clear if generation will make it easier for others to decode the music style of a particular artist.) "Music generation with Lyria 3 is designed for original expression, not for mimicking existing artists. If your prompt names a specific artist, Gemini will take this as broad creative inspiration and create a track that shares a similar style or mood. We also have filters in place to check outputs against existing content," the company said in a blog post. Google noted that all songs created with the Lyria 3 model will have a SynthID watermark to identify AI-generated content. The company said that it's also adding capabilities to identify AI-generated music with SynthID within Gemini. Users will be able to upload tracks and ask Gemini if it is AI-generated. Music generation is rolling out to all 18+ Gemini users across the world with support for English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. AI-generated music has created mixed sentiments among artists and listeners. On one hand, companies like YouTube and Spotify are adopting AI and signing contracts with music labels to monetize AI-generated music. On the other hand, AI model and tooling companies are facing lawsuits from the music industry over copyrights of the training material. Platforms like Deezer have published tools to mark AI-generated music to curb fraudulent streams of this kind of music.

Gemini Can Now Generate 30-Second Songs From Text, Images with Lyria 3

After image and video generation, it's time for music generation on Google's Gemini chatbot. The company just announced its latest music-generation model, Lyria 3, which will enable Gemini users to generate 30-second audio clips from textual and visual prompts. Getting started is as easy as generating images using Nano Banana. Click the "Create Music" button below the prompt box. You can choose from a set of tunes based on genres, such as 90s rap, Latin pop, R&B romance, Afropop, and more, or describe the mood, style, vocals, and tempo you'd like your track to have. Lyria 3 will also add lyrics based on your description, which can contain images for reference. Google's example for an image-based prompt says: "Use these photos to create a track about my dog Duncan on a hike in the woods." Once you hit Enter, Gemini will generate a 30-second clip with album art from Nano Banana. You'll be able to download the audio track and also share it using a link. The goal here isn't "to create a musical masterpiece, but rather to give you a fun, unique way to express yourself," Google says. The model is "designed for original expression, not for mimicking existing artists," and its filters should detect existing content. Additionally, all songs generated by Gemini will carry Google's Synth ID watermark. If you are unsure whether a clip was generated by Gemini, you can upload it to Gemini and ask the chatbot to verify. AI song generation isn't entirely new. Platforms like Suno and Udio have been at it for a couple of years, but they ran into copyright issues with major music labels like Sony, Universal Music, and Warner Bros. Suno settled its case with Warner, and Udio settled its case with Warner and Universal by signing licensing deals. YouTube was reportedly also considering licensing its AI tools in 2024. Earlier this month, it introduced AI Playlist generation for YouTube Premium and YouTube Music Premium. Lyria 3 in Gemini will roll out to all users aged 18+ on desktop starting today, and on the mobile app in the coming days. Gemini's music generation currently produces tracks in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Google plans to add support for additional languages in the future. Google didn't specify the limit for free users, but said that AI Plus, Pro, and Ultra subscribers will enjoy higher limits. The model will also be made available in YouTube's Dream Track tool for creating Shorts.

Google Gemini, Apple Add Music-Focused Generative AI Features

Alphabet Inc.'s Google and Apple Inc. are adding music-focused generative artificial intelligence features to their core consumer apps, underscoring how advanced AI tools are moving into mainstream use. Google's Gemini AI assistant can now create 30-second music tracks based on text, photos or video uploaded by users using Google DeepMind's latest Lyria 3 model, the company said in a blog post on Wednesday. The feature, which can generate custom lyrics or purely instrumental audio, will be available to users over the age of 18 in multiple languages. It is being rolled out on the desktop version of Gemini and will appear in the mobile app over the next few days, the company said. Its popular image-creation model, Nano Banana, will also generate custom cover art alongside the track, adding a visual element when users share links to the tracks with others, Google said. Adding audio-creation tools to its mobile app can potentially strengthen Google's consumer offerings as it remains locked in a race with OpenAI's ChatGPT to win over users. Google won widespread praise from investors and users for its Gemini 3 AI model released in November, prompting OpenAI Chief Executive Officer Sam Altman to declare a "code red" to spur faster ChatGPT improvements. Get the Tech Newsletter bundle. Get the Tech Newsletter bundle. Get the Tech Newsletter bundle. Bloomberg's subscriber-only tech newsletters, and full access to all the articles they feature. Bloomberg's subscriber-only tech newsletters, and full access to all the articles they feature. Bloomberg's subscriber-only tech newsletters, and full access to all the articles they feature. Bloomberg may send me offers and promotions. Plus Signed UpPlus Sign UpPlus Sign Up By submitting my information, I agree to the Privacy Policy and Terms of Service. Separately this week, Apple said consumers can soon use AI to create playlists in Apple Music. The feature, called Playlist Playground, uses Apple Intelligence to let people turn text prompts into playlists that will include cover art, description and 25 songs. It is included in iOS 26.4, which was released in beta on Monday and will become more widely available this spring. Apple Music's new feature rivals a similar one offered by Spotify Technology SA. Apple, which has been a laggard in artificial intelligence, is working to add more AI features across its apps and devices, including in its recently launched software bundle Creator Studio. But some highly anticipated updates to its Siri virtual assistant may be delayed after they were first announced in 2024, Bloomberg News reported last week. Google, for its part, has been working to show investors that its investments in AI-driven products can help boost revenue. For releases like this, that means the product is not completely free. Similar to how Gemini places limits on daily image creation, users of the free product can generate 10 tracks per day, while paying users get 20 to 100 daily depending on the plan their subscription tier. Users will have a right to use their generated tracks, the company said, adding it has filters in place to check outputs against existing content so that it doesn't violate intellectual property or privacy rules. Generative AI tools have been met with a wary, and sometimes hostile, reception from the music industry, which views some of the technology as a threat to its business and IP. In 2024, Universal Music Group NV, Warner Music Group Corp. and Sony Music Entertainment sued startups Suno AI and Uncharted Labs Inc., the developer of Udio AI, for copyright infringement. Warner Music has since settled with Suno, and both it and Universal Music have reached agreements with Udio to keep the app functioning with proper licensing and controls. Google said in the blog post that it has safeguards in place that prohibits the AI from lifting content from specific artists. If users name real musicians, Gemini will only take that prompt as "broad creative inspiration and create a track that shares a similar style or mood," it added. "Our training for Lyria 3 is designed to use music that YouTube and Google has a right to use under our terms of service, partner agreements and applicable law," a company spokesperson added.

I tried Gemini's new Lyria 3 in-app AI song generator -- and it turned my to-do list into a punk rock anthem

If you had fun with Nano Banana, hang on to your phones, because I think this is going to be the next new trend. Google is turning Gemini into a creative studio once again, but this time it's letting you make music. Starting today, the Gemini app is rolling out Lyria 3, its most advanced music generation model yet, allowing users to create 30-second songs from a simple text prompt or even a photo. The feature lets anyone produce short tracks complete with vocals, lyrics and cover art in seconds -- I've already played around with it and can honestly say it's a ton of fun. Just note that it's still in beta and may have a few hiccups. Here's how it works. How Gemini's AI music generator works The move expands Gemini's creative toolkit beyond images and video and signals Google's growing push into AI-powered creative expression. With Lyria 3, users can describe an idea -- or upload an image -- and Gemini generates a fully produced track to match. For example, I've already created: * A comical punk rock song for my husband's to-do list * An upbeat pop song to pump my son up for his soccer game * A fun day-in-the-life mom anthem Gemini then produces a 30-second track, complete with lyrics and AI-generated cover art created using Google's Nano Banana image model. Tracks can be downloaded or shared via a link, making them easy to send to friends or post on social media. I sent my husband's "to do list" song via text message. Google says the goal isn't to produce polished commercial songs, but to offer a fun, expressive way to add a custom soundtrack to everyday moments. How to try it Music generation with Lyria 3 is rolling out today on desktop and will arrive on mobile over the next few days. The feature is available to users 18 and older in multiple languages, including: English, Spanish, French, German, Hindi, Japanese, Korean and Portuguese. Google AI Plus, Pro and Ultra subscribers will receive higher generation limits. The model is also being integrated into YouTube's Dream Track, where it can help creators generate customized soundtracks for Shorts. Is AI music the future? Long before testing and reviwing AI, I worked with some of the biggest names in music from Justin Timberlake and John Legend to Amy Winehouse and legendary singer Carly Simon. I can honestly say, I don't believe AI will take over the music industry. But what I can see it doing is adding a synthetic layer beyond the studio -- giving everyday users the ability to sketch musical ideas, create playful tracks and turn memories into shareable sound in seconds. It's important to note for listeners and users that all music generated in Gemini includes SynthID, Google's imperceptible watermark designed to identify AI-generated content. In fact, Google is also expanding its verification tools: users can upload an audio file into Gemini and ask whether it was created with Google AI. The system checks for SynthID and uses additional analysis to determine its origin. To address copyright concerns, Google says Lyria 3 is designed for original expression rather than imitation. If a user references a specific artist, Gemini interprets the request as broad stylistic inspiration rather than direct mimicry. Filters and reporting tools are in place to prevent rights violations. The takeaway I've tested dozens of AI generated music tools, but Lyria 3 is different because it's so much easier to use. I think that embedding the tool inside such a popular mainstream assistant could bring generative audio to a much wider audience. It's now as easy and convenient to generate a song as it is an image. For creators, social media users and everyday Gemini fans, this update means turning inside jokes, memories or photos into shareable music in seconds. It's a ton of fun. Let me know in the comments what you think. Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds.

Google Gemini adds Lyria 3, an AI model that can create music with words and photos

Lyria 3 is now available on desktop, and will be rolling out to the Gemini mobile app in the coming days. Google is expanding the multimodal capabilities of Gemini, once again. Following the success of the viral Nano Banana image generator, the company is releasing Lyria 3, an AI model that can generate music. Google says you can get started with your words and describe what kind of music you want to generate, and the model will comply. Alternatively, you can feed it a picture or even a video, and Lyria 3 will generate a "high-fidelity track," with custom lyrics in tow. "From funny jingles to lo-fi beats, you can create custom 30-second soundtracks for any moment," says the company. Lyria 3 is already rolling out to the desktop version of Gemini, which you can access in a web browser. It will also be expanding to the Gemini mobile app for users in the coming days across the globe. What is Lyria 3 in Gemini? Lyria has been developed by Google's DeepMind division, which is at the frontier of pushing AI for cutting-edge innovations and research, such as using Gemini 3 Deep Think for turning sketches and ideas in 3D printing files. DeepMind is also behind the SynthID tech that puts an invisible watermark on media generated by AI tools. Recommended Videos With Lyria 3, Google is diving into a fun and controversial side of AI usage. The idea is pretty simple. You can pick any topic, idea, genre, or mood, and Gemini will create a 30-second sample for you. All you have to do is click on the tool picker in the Gemini chat box and select the new music option. How does it work? Just like image generation, or making videos in using Google's Veo engine, Lyria 3 will take your words, images, or videos, and create a fitting tune. If you are running out of creative ideas, there are plenty of templates where you can pick an existing track and modify it using prompts. It's somewhat like tweaking Gemini Gems or remixing mini-apps created in the Nothing Playground ecosystem. Using Lyria 3 in Gemini is free, in case you are wondering. I can imagine a lot of people sharing their photos and videos to create a suitable background track for posting on social media. Google won't be the first company to offer this convenience. Suno is the biggest name in the AI music generation segment, and has courted plenty of controversy for alleged copyright infringement.

Gemini Now Lets You Generate AI Music for Free

Paid subscribers can access higher usage limits, though Google doesn't specify what those are. Google Gemini can help you write text, generate images and video, and write code. Now, the AI bot can generate music too, taking on the likes of Suno when it comes to producing tunes from a simple text prompt. The update is courtesy of the new Lyria 3 audio generation model, which is built into Gemini as of today. Developed by Google DeepMind, Lyria has been accessible in other Google products (such as Vertex AI and YouTube Shorts) to a select number of users, but this is the first time Google is making the model widely available to anyone who wants to try it. Lyria works the same way as creating images or video: just describe what you want, and the AI does the rest. You might want to hear "a comical R&B slow jam about a sock finding their match" (as per Google's own example), or perhaps "a sea shanty about the dangers of AI slop" -- it's up to you. When you click the "Create music" button inside the Gemini app, you also have the option to pick an existing track to remix, rather than starting from scratch -- If you're perhaps stuck for inspiration. These presets cover everything from folk ballads to Latin pop, so you can see the kind of musical scope covered. You can also supply Lyria 3 inside Gemini with an image or video, and get it to compose something that matches the mood of the content you've supplied, including both music and lyrics. The example Google gives is supplying Gemini with a few photos of your dog, and then having it come up with a tune about the pooch and their adventures. The tracks are limited to 30 seconds each at the moment, and while music making is available to all Gemini users, if you're paying for the Plus, Pro, or Ultra subscriptions, you'll get higher usage limits (though it isn't specified what these are). As per the official announcement blog post, the aim "isn't to create a musical masterpiece, but rather to give you a fun, unique way to express yourself." You're not going to be able to set up your own AI-generated band on Spotify with this, but you can churn out a few entertaining tracks for your own (or someone else's) amusement. I haven't been able to try out the feature as of yet, but I have heard a few samples that Google supplied. They come across as rather generic and ordinary, exactly as you might expect something to sound that's the averaging out of vast amounts of audio training data -- like song genres distilled into their most common ingredients and repackaged. Google says all created tracks will contain invisible watermarks powered by SynthID, flagging them as AI creations, and you can upload audio tracks to Gemini and run a SynthID check on them. The updated Lyria 3 model is also coming to the Dream Track music maker for YouTube Shorts creators. Lyria 3 is now rolling out inside Gemini, and is available to users aged 18 and above in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. It's available first on the web app, and will show up on the mobile app over the next few days. Expansions in "quality and coverage" are planned in the future, Google says.