惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
V
Vulnerabilities – Threatpost
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
V
Visual Studio Blog
月光博客
月光博客
IT之家
IT之家
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
T
Tailwind CSS Blog
罗磊的独立博客
S
SegmentFault 最新的问题
博客园 - 三生石上(FineUI控件)
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
量子位
V
V2EX
Jina AI
Jina AI
The GitHub Blog
The GitHub Blog
小众软件
小众软件
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
阮一峰的网络日志
阮一峰的网络日志
Recent Announcements
Recent Announcements
MongoDB | Blog
MongoDB | Blog
Y
Y Combinator Blog
H
Help Net Security
博客园_首页
Cyberwarzone
Cyberwarzone
T
Tenable Blog
A
Arctic Wolf
C
CERT Recently Published Vulnerability Notes
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
Threat Research - Cisco Blogs
aimingoo的专栏
aimingoo的专栏
Google DeepMind News
Google DeepMind News
博客园 - 叶小钗
C
Cyber Attacks, Cyber Crime and Cyber Security
美团技术团队
Attack and Defense Labs
Attack and Defense Labs
GbyAI
GbyAI
博客园 - 【当耐特】
Cloudbric
Cloudbric
NISL@THU
NISL@THU
B
Blog RSS Feed
K
Kaspersky official blog
Hugging Face - Blog
Hugging Face - Blog
P
Privacy International News Feed
博客园 - Franky
博客园 - 司徒正美
Microsoft Azure Blog
Microsoft Azure Blog
Apple Machine Learning Research
Apple Machine Learning Research
Webroot Blog
Webroot Blog
Microsoft Security Blog
Microsoft Security Blog

Google DeepMind News

Investing in multi-agent AI safety research DiffusionGemma: 4x faster text generation Fluid, natural voice translation with Gemini 3.5 Live Translate Measuring the impact of learning with AI in Sierra Leone and beyond Powering the future of robotics in Europe Introducing Gemma 4 12B: a unified, encoder-free multimodal model Strengthening Singapore’s AI Future: A New National Partnership Simulate real-world places with Project Genie and Street View Introducing Gemini Omni Gemini for Science: AI experiments and tools for a new era of discovery Making it easier to understand how content was created and edited Gemini 3.5: frontier intelligence with action Co-Scientist: A multi-agent AI partner to accelerate research How WeatherNext helped the National Hurricane Center better predict Hurricane Melissa’s historic landfall in Jamaica Fast-tracking genetic leads to reverse cellular aging Finding the molecular switches behind new infectious diseases Opening new paths in aging research Accelerating discovery of liver disease mechanisms Uniting biological toolkits for a new approach to ALS Uncovering repurposed medicines to fight liver fibrosis Google Antigravity We’re launching the Google DeepMind Accelerator program in Asia Pacific to tackle environmental risks. Reimagining the mouse pointer for the AI era AlphaEvolve: How our Gemini-powered coding agent is scaling impact across fields Enabling a new model for healthcare with AI co-clinician Announcing our partnership with the Republic of Korea Decoupled DiLoCo: A new frontier for resilient, distributed AI training Partnering with industry leaders to accelerate AI transformation Gemini 3.1 Flash TTS: the next generation of expressive AI speech Gemini Robotics-ER 1.6: Powering real-world robotics tasks through enhanced embodied reasoning Gemma 4: Byte for byte, the most capable open models Gemini 3.1 Flash Live: Making audio AI more natural and reliable Protecting people from harmful manipulation Lyria 3 Pro: Create longer tracks in more Google products Measuring progress toward AGI: A cognitive framework From games to biology and beyond: 10 years of AlphaGo’s impact Gemini 3.1 Flash-Lite: Built for intelligence at scale Nano Banana 2: Combining Pro capabilities with lightning-fast speed Gemini 3.1 Pro: A smarter model for your most complex tasks Accelerating discovery in India through AI-powered science and education Gemini 3 Deep Think: Advancing science, research and engineering Accelerating Mathematical and Scientific Discovery with Gemini Deep Think Project Genie: Experimenting with infinite, interactive worlds D4RT: Teaching AI to see the world in four dimensions Veo 3.1 Ingredients to Video: More consistency, creativity and control Google's year in review: 8 areas with research breakthroughs in 2025 Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior Google DeepMind supports U.S. Department of Energy on Genesis: a national mission to accelerate innovation and scientific discovery Gemini 3 Flash: frontier intelligence built for speed Improved Gemini audio models for powerful voice interactions Deepening our partnership with the UK AI Security Institute Strengthening our partnership with the UK government to support prosperity and security in the AI era FACTS Benchmark Suite: Systematically evaluating the factuality of large language models Engineering more resilient crops for a warming climate AlphaFold: Five years of impact Revealing a key protein behind heart disease How we’re bringing AI image verification to the Gemini app Build with Nano Banana Pro, our Gemini 3 Pro Image model Introducing Nano Banana Pro We’re expanding our presence in Singapore to advance AI in the Asia-Pacific region Start building with Gemini 3 A new era of intelligence with Gemini 3 Google Antigravity WeatherNext 2: Our most advanced weather forecasting model SIMA 2: An Agent that Plays, Reasons, and Learns With You in Virtual 3D Worlds Teaching AI to see the world more like we do How AI is giving Northern Ireland teachers time back Mapping, modeling, and understanding nature with AI Accelerating discovery with the AI for Math Initiative MedGemma: Our most capable open models for health AI development VaultGemma: The world's most capable differentially private LLM Bringing AI to the next generation of fusion energy Introducing Veo 3.1 and advanced capabilities in Flow How a Gemma model helped discover a new potential cancer therapy pathway Introducing the Gemini 2.5 Computer Use model Introducing CodeMender: an AI agent for code security Gemini Robotics 1.5 brings AI agents into the physical world Strengthening our Frontier Safety Framework Discovering new solutions to century-old problems in fluid dynamics Gemini achieves gold-medal level at the International Collegiate Programming Contest World Finals Using AI to perceive the universe in greater depth Image editing in Gemini just got a major upgrade Introducing Gemma 3 270M: The compact model for hyper-efficient AI How AI is helping advance the science of bioacoustics to save endangered species Genie 3: A new frontier for world models Rethinking how we measure AI intelligence Try Deep Think in the Gemini app AlphaEarth Foundations helps map our planet in unprecedented detail Aeneas transforms how historians connect the past Gemini 2.5 Flash-Lite is now stable and generally available Exploring the context of online images with Backstory Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad T5Gemma: A new collection of encoder-decoder Gemma models Introducing Gemma 3n: The developer guide AlphaGenome: AI for better understanding the genome Gemini Robotics On-Device brings AI to local robotic devices We’re expanding our Gemini 2.5 family of models Gemini 2.5: Updates to our family of thinking models Behind “ANCESTRA”: combining Veo with live-action filmmaking How we're supporting better tropical cyclone prediction with AI
A new way to express yourself: Gemini can now create music
Joël Yawili · 2026-02-19 · via Google DeepMind News

The Gemini app now features our most advanced music generation model Lyria 3, empowering anyone to make 30-second tracks using text or images in beta.

Myriam Hamed Torres

Senior Product Manager, Google DeepMind

General summary

The Gemini app now lets you create custom music using Google DeepMind’s Lyria 3. Just describe an idea or upload a photo, and Gemini will generate a 30-second track with custom cover art. Also, all tracks generated in the Gemini app are embedded with SynthID, our imperceptible watermark for identifying Google AI-generated content.

Summaries were generated by Google AI. Generative AI is experimental.

Bullet points

  • Gemini's new feature, using Lyria 3, lets you create custom music from text or images.
  • Just describe your idea, and Gemini will generate a 30-second track with custom cover art.
  • Lyria 3 improves on previous models with lyrics, creative control, and complex tracks.
  • SynthID watermarks all Gemini-generated music, and you can verify if audio is AI-made.
  • Available in the Gemini app for users 18+ in multiple languages, with higher limits for subscribers.

Summaries were generated by Google AI. Generative AI is experimental.

Basic explainer

The Gemini app can now make music using Google's new AI model, Lyria 3. You can type in a description or upload a photo, and Gemini will create a short song based on it. The AI adds a special code to the music, so people know it was made by AI. This new feature is supposed to help people express themselves in a fun way.

Summaries were generated by Google AI. Generative AI is experimental.

Explore other styles:

Since launching the Gemini app, we've built tools to encourage creative expression through images and video. Today, we're taking the next step: custom music generation. Lyria 3, Google DeepMind’s latest generative music model, is rolling out today in beta in the Gemini app. Just describe an idea or upload a photo, like “a comical R&B slow jam about a sock finding their match" and in a matter of seconds, Gemini will translate it into a high-quality, catchy track. To push the creative envelope further, you can even ask Gemini to take inspiration from something you upload.

Lyria 3 improves on audio generation from our Lyria models in three important ways:

  1. No need to provide your own lyrics! They'll be generated for you based on your prompt.
  2. You have more creative control over elements like the style, vocals and tempo you want.
  3. You can create more realistic and musically complex tracks.

Here’s how you can use it:

  • Text to track: Describe a specific genre, mood, inside joke, or memory to create unique tracks with lyrics or instrumental audio that fits your vibe. “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.”
  • From photos and videos to track: Upload a photo or video and watch Gemini use the content to compose a track with lyrics that fit the mood perfectly. “Use these photos to create a track about my dog Duncan on a hike in the woods.”

The Gemini app creates 30-second tracks with custom cover art generated by Nano Banana. This makes it easy to quickly share with friends by downloading or simply clicking the share link. The goal of these tracks isn't to create a musical masterpiece, but rather to give you a fun, unique way to express yourself.

Your browser does not support the audio element.

Creators can also explore Lyria 3 on YouTube’s Dream Track. Available in the U.S. and now rolling out to YouTube creators in other countries, Lyria 3 will enhance the quality of each unique Shorts soundtrack. Whether it's creating a lyrical verse or a vibey backing track, being able to better customize the soundtrack will take creators’ Shorts to the next level.

New audio verification capabilities

All tracks generated in the Gemini app are embedded with SynthID, our imperceptible watermark for identifying Google AI-generated content. We are also giving you more tools to help identify AI content, broadening our verification capabilities in the Gemini app to include audio, along with image and video. Simply upload a file and ask if it was generated using Google AI, and Gemini will check for SynthID and use its own reasoning to return a response.

Our commitment to developing generative AI responsibly

Since we first launched Lyria in 2023, we've sought to develop this technology responsibly in collaboration with the music community. We've learned a lot through these collaborations and our experiments, like Music AI Sandbox, and have been very mindful of copyright and partner agreements as we've trained Lyria 3.

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. We recognize that our approach might not be foolproof, so you can report content that may violate your rights or the rights of others. Additionally, in order to use our products, users must adhere to our Terms of Service and Gen AI prohibited use policies, which prohibit violations of others’ intellectual property and privacy rights.

Lyria 3 is available in the Gemini app for all users 18+ in English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese, with plans to expand quality and coverage of more languages, rolling out on desktop today and to the mobile app over the next several days. And Google AI Plus, Pro and Ultra subscribers will enjoy higher limits.

Our goal with music generation in the Gemini app is to help you add a fun, custom soundtrack to your daily life. Try it out today at gemini.google.com.

Related stories