# Gemini Now Lets You Create AI-Generated Music
Google has introduced a groundbreaking feature that brings AI-powered music generation directly to Gemini, enabling users to create professional-quality tracks with vocals and lyrics from simple text prompts. The new Lyria 3 model represents a significant leap forward in democratizing music creation, allowing anyone—regardless of musical experience—to generate 30-second compositions instantly[4][5].
How Google Gemini's Music Generation Works
The Lyria 3 music generation tool in Gemini operates through an intuitive, prompt-based interface that transforms your creative vision into audio[4]. Users can generate high-quality, 30-second tracks by simply describing what they want to create, whether that's a specific mood, genre, or instrumentation style[5]. The system also supports image-to-music generation, allowing you to upload images and have Gemini create accompanying music based on visual content[5].
The underlying technology uses Lyria RealTime, Google's state-of-the-art streaming music generation model that provides real-time, interactive music creation capabilities[2]. This means you're not limited to static generation—you can continuously steer and refine the music as it's being created, adjusting elements like mood, instrumentation, and overall direction on the fly[2].
Key Features and Creative Capabilities
Gemini's music generator includes several powerful features designed to enhance your creative workflow. The tool supports an extensive range of mood and description parameters, including options like ambient, dreamy, lo-fi, psychedelic, upbeat, and many others[2]. This granular control allows creators to specify exactly the emotional tone and sonic character they want their tracks to have.
The vocal generation capability sets this tool apart from earlier iterations, enabling the creation of complete songs with lyrics and instrumentation rather than just instrumental backgrounds[5]. Users can also leverage the real-time steering functionality, which allows them to send new prompts while music is generating to smoothly transition the track based on fresh input[2].
Integration and Accessibility
What makes Gemini's music generation particularly significant is its seamless integration into the broader AI ecosystem. Developers can access the Gemini API to build custom applications incorporating Lyria RealTime, opening possibilities for businesses, content creators, and musicians[2]. For everyday users, the feature is accessible directly through the Gemini interface, eliminating the need to switch between multiple tools or platforms.
The music generation capability also pairs effectively with other content creation tools, particularly for creators producing multimedia content[3]. Musicians and producers can generate tracks with Gemini, then integrate them into video projects or further refine them in digital audio workstations (DAWs)[3].
Frequently Asked Questions
What is Lyria 3 and how does it differ from previous music generation models?
Lyria 3 is Google's latest music generation model available in Gemini, capable of creating 30-second tracks with vocals and lyrics from text prompts or images[4][5]. It represents a significant advancement over earlier models by supporting vocal generation, real-time steering of music during creation, and a broader range of creative parameters[2].
Can I generate music with specific genres or moods?
Yes, Lyria 3 supports an extensive range of mood and description parameters, including acoustic instruments, ambient, chill, danceable, dreamy, lo-fi, psychedelic, upbeat, and many others[2]. You can specify your desired mood, genre, instrumentation, and emotional tone directly in your prompt.
How long are the generated tracks?
The tracks generated through Gemini's Lyria 3 model are 30 seconds in length[4][5]. This duration is suitable for background music, social media content, video intros, and other short-form creative applications.
Can I upload images to generate music?
Yes, Gemini's music generator supports image-to-music generation, allowing you to upload images and have the system create accompanying music based on the visual content[5]. This feature enables creative workflows where visuals inspire the soundtrack.
Is the generated music royalty-free?
While the search results confirm that modern AI music generators can produce royalty-free tracks for commercial use[3], specific licensing details for Gemini's Lyria 3 output should be verified in Google's official terms of service and licensing documentation.
Can developers integrate this into their own applications?
Yes, developers can access the Gemini API with Lyria RealTime capabilities to build custom applications incorporating music generation[2]. The API supports real-time streaming, weighted prompts for steering music, and various playback control options, enabling developers to create specialized music generation tools for their platforms.
🔄 Updated: 2/18/2026, 4:11:04 PM
I cannot provide a news update confirming that "Gemini now lets you create AI-generated music" because the search results indicate this feature has not been officially released. According to source code analysis, Google is **developing** a native music generation feature for Gemini on Android, but it "has not been announced" and remains in development stages.[1] Since the feature does not yet exist as a consumer product, there is no regulatory or government response to report on its actual launch.
However, the search results do show that governments are actively addressing AI music generation concerns more broadly. India's government is working to "build a broad national consensus that safeguards creators, protects their original work, and enables innovation to flourish
🔄 Updated: 2/18/2026, 4:21:01 PM
**BREAKING: Google’s Gemini App Rolls Out Lyria 3 Music Generation Globally, Sparking Mixed International Reactions.** The feature, now available in beta to all users 18+ worldwide in **8 languages**—English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese—enables instant creation of **30-second AI tracks** from text prompts or images, with SynthID watermarks for verification[1][2][3]. While platforms like YouTube expand it via Dream Track (US-only now, rolling out elsewhere), artists voice concerns over copyrights, citing ongoing lawsuits against AI firms and tools from Deezer to combat fraudulent AI streams[1]. Google emphasizes responsible development: *"We’ve been very mindfu
🔄 Updated: 2/18/2026, 4:31:13 PM
I cannot provide the market reactions and stock price movements you've requested, as the search results contain no information about investor sentiment, stock performance, or financial market responses to Google's Lyria 3 announcement[1][2][3][4][5][6]. The available sources focus exclusively on the product features—30-second music generation from text prompts or images, global rollout to 18+ users, and competitive positioning against startups like Suno and Udio—but do not include any financial or trading data.
To answer your query properly, I would need sources covering stock market analysis, investor commentary, or financial reporting on this announcement.
🔄 Updated: 2/18/2026, 4:41:12 PM
Google has rolled out **music generation to the Gemini app** using DeepMind's Lyria 3 model, enabling users to create 30-second tracks with lyrics by describing a song concept or uploading photos and videos[2][3]. The feature generates "more realistic and musically complex music tracks" with user control over style, vocals, and tempo, while incorporating a SynthID watermark to identify AI-generated content and prevent unauthorized artist mimicry[2][4]. The capability is available to all users 18 and older globally in eight languages, with Gemini also gaining the ability to detect whether uploaded audio was AI-generated[2][3].
🔄 Updated: 2/18/2026, 4:51:08 PM
I cannot provide the market reaction and stock price movements you've requested because the search results do not contain that information. The available sources focus exclusively on the technical features of Google's Lyria 3 music generation integration into Gemini—including the 30-second track generation, supported languages, and AI watermarking capabilities—but include no financial market data, investor sentiment, or stock price information related to this announcement.
To provide an accurate news update with concrete numbers and quotes about market reactions, I would need sources covering financial markets, investor analysis, or company earnings discussions related to this feature launch.
🔄 Updated: 2/18/2026, 5:01:10 PM
**BREAKING: Google rolls out Lyria 3 music generation to Gemini app worldwide for all users 18+.** The beta feature, powered by DeepMind’s most advanced model, creates **30-second tracks with lyrics, cover art via Nano Banana, and user controls for style, vocals, and tempo** from text prompts like “a comical R&B slow jam about a sock finding its match” or uploaded photos/videos matching their mood[1][2][3]. All outputs carry **SynthID watermarks** for AI detection, with filters blocking artist mimicry—“designed for original expression, not for mimicking existing artists”—and support in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese
🔄 Updated: 2/18/2026, 5:11:09 PM
Google has deployed **Lyria 3 music generation directly into its Gemini app**, reshaping the competitive landscape by bundling a capability that startups like Suno and Udio built standalone subscriptions around—a "classic platform play" that pressures independent music AI companies.[1] The rollout to 100+ million Gemini users worldwide marks Google's first major tech platform to integrate music generation into a general-purpose AI assistant, positioning it ahead of OpenAI and Anthropic, which have focused on text and reasoning rather than creative production.[1][2] According to Google's Senior Product Manager Joël Yawili, the feature represents "a new way to express yourself" through
🔄 Updated: 2/18/2026, 5:21:08 PM
Google has launched **Lyria 3 beta** in the Gemini app, enabling users to generate 30-second AI music tracks from text prompts, images, or videos without leaving the chat interface.[1][2] The DeepMind model automatically generates lyrics and allows fine-tuning of style, vocals, and tempo, representing a significant shift toward multimodal AI where creation—not just understanding—of different media types happens in one unified platform.[2][4] The rollout reaches 100+ million Gemini users aged 18+ across eight languages, with all generated tracks embedded with **SynthID watermarks** for AI-content identification and detection capabilities built directly into Gemini.[
🔄 Updated: 2/18/2026, 5:31:09 PM
Google has launched **Lyria 3 music generation** directly in the Gemini app, enabling users to create **30-second AI-generated tracks** from text prompts, images, or videos with automatic lyric generation and customizable style, vocals, and tempo controls[1][2]. The rollout reaches **100+ million Gemini users** globally across eight languages with all generated content embedded with **SynthID watermarks** for AI identification, while Gemini can now detect whether uploaded audio was created using Google AI[2][3]. This move consolidates Google's multimodal creative capabilities—previously scattered across separate tools for text, images, and video—into a unified interface, intensifying competition
🔄 Updated: 2/18/2026, 5:41:06 PM
**BREAKING: Google Gemini Rolls Out Lyria 3 Beta for AI Music Generation**
Industry experts hail Google's integration of DeepMind's **Lyria 3** into the Gemini app as a "biggest play yet in AI-generated audio," enabling over **100 million users** aged 18+ to create **30-second tracks** from text prompts like “upbeat jazz for a rainy afternoon” or uploaded images/videos, with controls for style, vocals, and tempo[1][2]. Analysts note it advances multimodal AI creativity beyond text and images, featuring **SynthID watermarks** for verification and global rollout in eight languages, though designed "for original expression, not mimicking artists" per Google, amid copyright safeguard
🔄 Updated: 2/18/2026, 5:51:08 PM
Google has launched **Lyria 3**, its latest music generation model, directly in the Gemini app, allowing the platform's 100+ million users worldwide to create custom 30-second tracks from text prompts, images, or videos.[1][2] The feature is rolling out today to all users 18 and older across the globe with support for eight languages—English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese—marking Google's most significant expansion of creative AI capabilities into music production.[3][4] The move positions Google in direct competition with standalone startups like Suno and Udio, while simultaneously extending Lyria 3 availability to YouTube creators internationally through the
🔄 Updated: 2/18/2026, 6:01:13 PM
Google has integrated **DeepMind's Lyria 3 music generation model** directly into the Gemini app, enabling users to create **30-second tracks** from text prompts, images, or videos without leaving the chat interface[1][2]. The rollout reaches **100+ million Gemini users** aged 18 and older across eight languages (English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese), with Lyria 3 offering improved control over style, vocals, and tempo compared to earlier iterations[1][2][4]. All generated tracks are embedded with **SynthID watermarks** to identify AI-generated content, and users can now upload audio
🔄 Updated: 2/18/2026, 6:11:09 PM
Google's Gemini app rollout of Lyria 3 beta enables over **100 million users globally** to generate 30-second AI music tracks from text, images, or videos, instantly accessible in eight languages including English, Hindi, Japanese, Korean, German, Spanish, French, and Portuguese for those 18+.[1][2][3][5] This expansion, embedding SynthID watermarks for AI detection and extending Dream Track to international YouTube creators beyond the U.S., intensifies competition with startups like Suno and Udio amid booming generative audio demand.[1][3][4] Google emphasizes responsible development through music industry collaborations since Lyria's 2023 launch, addressing copyright concerns without reported international backlash yet.[4]
🔄 Updated: 2/18/2026, 6:21:05 PM
Google has integrated **Lyria 3**, DeepMind's latest music generation model, directly into the Gemini app, enabling users to create 30-second tracks from text prompts, images, or videos without leaving the interface[1][2]. The feature generates original lyrics and cover art automatically, with users able to control style, vocals, and tempo, while all tracks are embedded with **SynthID watermarks** for AI-generated content identification[2][4]. The rollout reaches 100+ million Gemini users aged 18+ globally across eight languages, positioning Google's push into multimodal creative AI as it competes with OpenAI and Meta in consumer generative capabilities[1][
🔄 Updated: 2/18/2026, 6:31:11 PM
I cannot provide the regulatory or government response you've requested because the search results contain no information about government or regulatory reactions to Google's new music generation feature in Gemini. The search results focus on the technical capabilities of Lyria 3, market impact on Spotify's stock, and broader AI adoption trends, but do not include any statements or actions from regulators or government officials regarding this specific announcement.