/
Navigation
C
Chronicles
Browse all articles
C
E
Explore
Semantic exploration
E
R
Research
Entity momentum
R
N
Nexus
Correlations & relationships
N
~
Story Arc
Topic evolution
S
↻
Drift Map
Semantic trajectory animation
D
P
Posts
Analysis & commentary
P
Browse
@
Entities
Companies, people, products, technologies
◇
Domains
Browse by publication source
☉
Handles
Browse by social media handle
Detection
?
Concept Search
Semantic similarity search
!
High Impact Stories
Top coverage by position
+
Sentiment Analysis
Positive/negative coverage
*
Anomaly Detection
Unusual coverage patterns
Analysis
vs
Rivalry Report
Compare two entities head-to-head
/\
Semantic Pivots
Narrative discontinuities
!!
Crisis Response
Event recovery patterns
Connected
Nav: C E R N
Search: /
Command: ⌘K
Embeddings: large
VOICE ARCHIVE

Jason Baldridge

@jasonbaldridge
7 posts
2026-02-19
I joined @OfficialLoganK, @myriam_hamed and Jeff Chang for a discussion on Lyria 3! We share samples, discuss its making, how we see it being used, and more. We see it as a instrument, one that is both weird and interesting. (We're gonna get Logan listening to more music!) ↓
2026-02-19 View on X
The Keyword

Google rolls out Lyria 3, a generative music model to make 30-second tracks with Nano Banana-generated cover art, in beta in the Gemini app in eight languages

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.

View original
Our team has been working incredibly hard on creating Lyria 3 this past year! (And it's been pretty much my full focus since moving to London last summer.) Really excited to get this out and for people to start playing with it and creating. Check it out in Gemini App today!
2026-02-19 View on X
The Keyword

Google rolls out Lyria 3, a generative music model to make 30-second tracks with Nano Banana-generated cover art, in beta in the Gemini app in eight languages

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.

View original
Two Lyria 3 tracks I made: an EDM hype track (Lyria, let's go!) and then a quirky one on launching it — tiring, but exciting. (One of the things we focused on was making Lyria 3 weird-able.) Try it! https://gemini.google.com/ @GeminiApp @GoogleDeepMind [video]
2026-02-19 View on X
The Keyword

Google rolls out Lyria 3, a generative music model to make 30-second tracks with Nano Banana-generated cover art, in beta in the Gemini app in eight languages

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.

View original
2026-02-18
Our team has been working incredibly hard on creating Lyria 3 this past year! (And it's been pretty much my full focus since moving to London last summer.) Really excited to get this out and for people to start playing with it and creating. Check it out in Gemini App today!
2026-02-18 View on X
The Keyword

Google rolls out Lyria 3, a generative music model that can make 30-second tracks with Nano Banana-made cover art, in beta in the Gemini app in eight languages

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.

View original
2024-12-17
Whisk is a really fun and compelling new way to prompt our Imagen 3 model. You upload images that have subject, scene or style of interest, and then it composes these together to generate a new image based on these elements. Less wordsmithing, and fun results!
2024-12-17 View on X
The Verge

Google debuts Whisk, an image generator that takes other images as prompts to suggest the subject, scene, and style, and uses the new, “latest” Imagen 3 version

Google has announced a new AI tool called Whisk that lets you generate images using other images as prompts instead of requiring a long text prompt.

View original
2024-08-16
Excited to share our paper about Imagen 3, Google's latest and most capable text-to-image model! https://arxiv.org/... It's been a big team effort. You can try it out on ImageFX, our experimental AI tech surface, now: https://aitestkitchen.withgoogle.com/ ...
2024-08-16 View on X
VentureBeat

Google makes Imagen 3 available to all US users via ImageFX, after unveiling the text-to-image AI model in May; some users criticize its strict content filters

Google has quietly made its latest text-to-image AI model, Imagen 3, available to all U.S. users through its ImageFX platform …

View original
Imagen 3 is also powering new features such as #PixelStudio, which is launching in preview on ur Pixel 9 devices. https://x.com/...
2024-08-16 View on X
VentureBeat

Google makes Imagen 3 available to all US users via ImageFX, after unveiling the text-to-image AI model in May; some users criticize its strict content filters

Google has quietly made its latest text-to-image AI model, Imagen 3, available to all U.S. users through its ImageFX platform …

View original