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

博客园 - 叶小钗
D
Docker
Google DeepMind News
Google DeepMind News
Y
Y Combinator Blog
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
Blog — PlanetScale
Blog — PlanetScale
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
U
Unit 42
博客园 - 【当耐特】
N
Netflix TechBlog - Medium
V
Visual Studio Blog
Microsoft Azure Blog
Microsoft Azure Blog
博客园_首页
Recent Announcements
Recent Announcements
GbyAI
GbyAI
T
Tailwind CSS Blog
S
SegmentFault 最新的问题
WordPress大学
WordPress大学
T
The Blog of Author Tim Ferriss
Engineering at Meta
Engineering at Meta
L
LangChain Blog
A
About on SuperTechFans
M
MIT News - Artificial intelligence
B
Blog

AI

AI for Societal Impact Building AI to accelerate science and improve lives AI for everyone in every language New insights from Google’s AI & Economy ATLAS Watch astronaut Christina Koch and Google’s James Manyika discuss space, technology, and discovery. DevFest is back 3 ways to prep for your next big race with Search Get ready for the game with new football features in Search Recreating a 70-year love story frame by frame Proactive cyber defense for governments and enterprises The latest AI news we announced in August 2026 Try Google Pics: Easy image creation and editing in Google Workspace 3 new ways to plan and book travel in Search 5 ways to upgrade your home decor with Google Search 5 new ways to level up your learning with Search Get closer to the game with Gemini and Pixel Bring your spreadsheet data to life with Sheets canvas AMIE, our research medical AI system, demonstrates real-time clinical video consultation capabilities in a first-of-its-kind study. Evolve your marketing with new AI tools The latest AI news we announced in July 2026 Inside our 353,000-person vibe coding course Gemini API Managed Agents: 3.6 Flash, hooks, and more 5 ways AI Mode in Search helps you enjoy the real world 5 ways to host the ultimate dinner party with Google Search 3 Google updates from Galaxy Unpacked 2026 Connect more of your apps to Search Create, edit and star in videos with two Google Vids updates Celebrating 25 years of visual search innovation Expanding Managed Agents in Gemini API: background tasks, remote MCP and more The latest AI news we announced in June 2026
Build with Lyria 3, our newest music generation model
Alisa Fortin · 2026-03-26 · via AI

Our newest music generation model is now available to developers in public preview.

Guillaume Vernade

Gemini Developer Advocate, Google DeepMind

General summary

Lyria 3 music generation models are here for developers through the Gemini API and Google AI Studio. You can choose between Lyria 3 Pro for full songs or Lyria 3 Clip for shorter clips, and control tempo, lyrics, and even use images to influence the music. Start experimenting in AI Studio today and check out the documentation and cookbook to start coding.

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

Bullet points

  • "Build with Lyria 3" introduces Google's new music generation models for developers.
  • Lyria 3 Pro creates full songs, while Lyria 3 Clip makes shorter, high-quality clips.
  • Control tempo, lyrics, and mood using text prompts or even images as input.
  • Use Google AI Studio to experiment with Lyria 3 and build custom music apps.
  • Lyria 3 adds a digital watermark to tracks, ensuring transparency and trust.

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

Explore other styles:

Your browser does not support the audio element.

Listen to article

This content is generated by Google AI. Generative AI is experimental

[[duration]] minutes

Lyria 3 and Lyria 3 Pro, our music generation models, are rolling out now to developers in public preview through the Gemini API and a new audio experience in Google AI Studio.

Lyria 3 is designed to combine deep musical awareness with structural coherence. This allows developers to build apps that offer high-fidelity compositions, including vocals, verses and choruses, that maintain musical consistency from the first note to the last.

Studio quality and speed

Developers can now choose between two distinct model variants designed to meet specific production and latency requirements:

  • Lyria 3 Pro (lyria-3-pro-preview): Our premier model for full-length song generation creates tracks up to approximately three minutes long. These tracks have professional-grade structural awareness, making it the standard for studio-quality, premium output.
  • Lyria 3 Clip (lyria-3-clip-preview): Optimized for speed and high-volume requests, this variant generates high-quality 30-second clips. It is the ideal choice for rapid prototyping, background loops and social media assets.

Both models support realistic vocals that convey expressive nuance, plus improved clarity for more natural sounds. Developers can also explore global languages and genres. Generate vocals in different languages, and create music spanning genres from pop to funk to Motown.

Precision control and multimodal input

Lyria 3 introduces granular controls that allow you to direct the model with precision through natural language prompts:

  • Tempo conditioning: Set a specific tempo (e.g., Fast, slow) with high accuracy to ensure the music fits your application’s rhythm.
  • Time-aligned lyrics: You can outline the progression of a song in your prompt and control when lyrics start and end within a track.
  • Multimodal image-to-music input: Beyond text, Lyria 3 supports multimodal inputs. You can provide an image to influence the mood, style and atmosphere of the audio.

Lyria 3 in action

To show how you could incorporate this model into an application we built some examples in Google AI Studio:

  • Background music for videos: This demo app allows users to upload a video that is analyzed by Gemini 3 flash to generate a descriptive prompt for a custom soundtrack. Lyria then uses this prompt to compose a matching instrumental that serves as a synchronized background music for the video.
  • Alarm clock: This demo app wakes you up each morning with a new song that covers relevant information like the weather, your location, the time and date, and events on your calendar.

Try Lyria 3 in Google AI Studio

To help you start experimenting immediately, we are also launching a new music generation experience in AI Studio. Using a paid API key, this dedicated workspace provides a first-class environment to create with Lyria 3 and explore its advanced features like image to music.

Inside the playground, you can explore two powerful creation modes for music:

  1. Text mode: Describe the music you want to hear using natural language including parameters like Tempo or Key.
  2. Composer mode: Build your song section by section from intro to verses, to bridges and more. This mode gives you granular control to set timing, intensity and descriptions for each part individually.

Start composing today

Lyria 3 Clip and Lyria 3 Pro are now available in public preview for developers globally.

We have been developing our music generation tools in close partnership with industry experts to ensure AI serves as an additive force for human creativity. Additionally, every track generated by Lyria 3 includes a SynthID digital watermark. This technology maintains transparency and trust by allowing anyone to identify and verify audio generated by Google AI, even after the audio has been modified.

Related stories