Subvolts take Google's Lyria 3 model transforms creative intent into music, acting as a new instrument. Feb 18, 2026 - Developers
- Learn about Lyria 3's capabilities and opportunities for developers in AI music generation.
- Business
- Understand how generative AI is evolving in creative fields like music production.
- Everyday users
- Discover how AI is making music creation more accessible to everyone, regardless of skill.
This episode features a deep dive into Google's latest music AI, Lyria 3, by members of the team that built it.
Inside Lyria 3, Google's music generation model
Audio streams from Google AI. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Logan Kilpatrick hosts Jeff Chang, Myriam Hamed Torres, and Jason Baldridge from Google DeepMind to discuss Lyria 3, Google's latest music generation model. The episode explores how Lyria 3 transitions from simple audio generation to enabling creative intent, acting as a new instrument. Demos showcase instrumental funk and vocal exploration, highlighting Lyria's potential for both musicians and non-musicians.
This episode explains Lyria 3, Google's new AI that creates music. It shows how people can use words to guide the AI, making music creation easier for everyone, not just musicians.
This episode offers a look into Google's advancements in generative AI for music, specifically Lyria 3. It's for AI researchers, musicians, and developers interested in creative AI tools. The discussion on connecting language to creative intent and empowering new musical expressions aligns with current frontier lab efforts in multimodal AI and democratizing creative processes.
- HostLogan Kilpatrick
- GuestJeff ChangGoogle DeepMind
- GuestMyriam Hamed TorresGoogle DeepMind
- GuestJason BaldridgeGoogle DeepMind
- Episode Title: Inside Lyria 3, Google's music generation model
- Show: Google AI: Release Notes
- Length: 37 minutes
- Guests: Jeff Chang, Myriam Hamed Torres, and Jason Baldridge from Google DeepMind
- Topic: Google's latest music generation model, Lyria 3
1:00 - Defining music generation models
1:40 - Lyria as a new instrument
3:05 - Connecting language and creative intent
5:08 - Guest backgrounds and musical journeys
7:57 - Demo: Instrumental funk jam
8:29 - Bridging the gap for non-musicians
12:03 - Demo: Exploring lyrics and vocals
15:07 - The magic of iterative co-creation
15:40 - Meeting users across the expertise spectrum
17:01 - Empowering new musical expressions
18:29 - Emotional and communal impact of music
19:51 - Opportunities for developers and community
21:09 - Real-time vs. song generation models
23:23 - Creating experimental sonic landscapes
25:08 - Demo: Capturing unexpectedness and energy
28:33 - Evaluating music through taste and expertise
31:30 - The diligence of music evaluation
31:52 - The future of Lyria and AI-first workflows
35:07 - Articulating creative vision through languag
- generative AI
- AI that can create new content, like music or text.
- AI that can make new things.
- creative intent
- The specific artistic goal or idea a user wants the AI to achieve.
- What you want the AI to create.
27 minKoray Kavukcuoglu on frontier models, coding agents, and building AGI
WithKoray Kavukcuoglu
39 minIntroducing Gemini Robotics 2
WithCarolina Parada, Stuart Bowers, Kanishka Rao, Jie Tan
42 minGemini co-leads on project origins and what's next
WithJeff Dean, Koray Kavukcuoglu, Noam Shazeer, Oriol Vinyals
40 min
1 h 35Can AI Replace Teachers? Inside the $40M Company Using AI Tutors to Teach 200% Faster | #233
WithMackenzie Price, Joe Lamont
57 min
58 minAI’s Capital Flywheel: Models, Money, and the Future of Power
WithMartin Casado, Sarah Wang
1 h 11Questions people ask
- What is Lyria 3?
- Lyria 3 is Google's latest music generation model, designed to transition from simple audio generation to understanding and executing creative intent.
- How does Lyria 3 help non-musicians?
- The model aims to bridge the gap for non-musicians by allowing them to explore lyrics and vocals, and empowering new musical expressions through co-creation.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Google AI.