/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
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
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

YouTube lets some Shorts creators test Dream Track, a new DeepMind-powered AI tool to generate and remix music in the styles of nine artists, including Sia

YouTube creators will get to test a new AI tool that generates and remixes music in the style of several famous musicians, including Sia, Demi Lovato, and T-Pain.

Wired Will Knight

Context & Ripple Effects

Dream Track moves YouTube’s generative-AI effort from reported label-rights discussions toward a limited creator experiment. The following day, YouTube outlined the underlying Lyria-based music tooling in its Dream Track and Music AI preview.

The test also foreshadows a later, narrower creator control: YouTube subsequently tested prompt-based restyling of licensed songs for Shorts. Together, the coverage shows music generation being embedded in the Shorts creation flow rather than offered as a standalone product.

First-order effects

  • Selected Shorts creators can generate or remix music in the styles of a small set of participating artists, reducing the effort needed to add tailored audio to short videos.
  • YouTube and the named artists gain an early test bed for how artist-style AI music performs inside a major distribution surface.

Second-order effects

  • Record labels and artists have a concrete platform model to evaluate: limited access to style-based generation can create a licensing and approval path distinct from unrestricted voice or music imitation.
  • Competing short-video platforms and music-creation tools face pressure to pair generative audio with recognizable artist participation, not just generic soundtrack generation.

Third-order effects

  • If these controlled tests expand, music-rights holders may increasingly negotiate AI-generation permissions as a platform-distribution product, with access and attribution rules built into creator tools.
  • The broader shift is toward vertically integrated creation stacks in which the platform supplies both generative media and the audience; the durability of that model depends on rights-holder terms and creator uptake.

The trend: This is an early instance of AI content commercialization moving generative music into a platform-native creator workflow under artist participation.

Discussion

  • @mealreplacer Julian Hazell on x
    Defs gonna get T-Pain to sing “you are trying to solve the wrong problem using the wrong methods based on a wrong model of the world derived from poor thinking and unfortunately all of your mistakes have failed to cancel out”
  • @andrewcurran_ Andrew Curran on x
    Google has released Lyria. Late night big reveal. Everyone has been waiting for the breakthrough in generative music, maybe this is it.
  • @leokelion Leo Kelion on x
    This is fascinating. Both in terms of how it's being pitched as a tool for musicians, and the craft put into the announcement video (still a place for humans, at least for now!) Well worth a watch #DeepMind #AI #Music https://deepmind.google/...
  • @jannespijkervet Janne Spijkervet on x
    DeepMind's Lyria is here. A remarkably strong and diverse set of music making tools for creators on YouTube. It's the beginning of a new era for the entire music industry.
  • @sedielem Sander Dieleman on x
    5-6 years ago I was working on music generation at DeepMind, but let me tell you, this is... something else. Incredibly excited to be able to finally share what our team has been working on!
  • @giffmana Lucas Beyer on x
    This model is reeeeeeally good
  • @keunwoochoi Keunwoo Choi on x
    THIS IS BIG! All the music folks in Google Deepmind focus on one thing: AI music generation while NOT exploiting artists. Nothing is perfect, there're probably still some holes in giving the credit, but this is better than anything ever for very sure.
  • @demishassabis Demis Hassabis on x
    Thrilled to share #Lyria, the world's most sophisticated AI music generation system. From just a text prompt Lyria produces compelling music & vocals. Also: building new Music AI tools for artists to amplify creativity in partnership w/YT & music industry https://deepmind.google/…
  • @pushmeet Pushmeet Kohli on x
    Really happy to share that as part of the Lyria release, our team @GoogleDeepMind have extended SynthID, our state of the art system for watermarking and detecting AI generated content to detect AI generated audio. For more details on SynthID, see: https://deepmind.google/... [im…
  • @vaibhavk97 Vaibhav Kumar on x
    The age of one-person studios is here: Art: @runwayml + @midjourney Voice: @elevenlabsio Script: GPT-4 Music: Lyria
  • @googledeepmind @googledeepmind on x
    Today with @YouTube, we're announcing Lyria: our most advanced music generation model to date. 🎶 We're also releasing 2️⃣ AI experiments in close collaboration with participating artists and creators to bring their ideas to life responsibly. → https://deepmind.google/... [image]
  • @andrewcurran_ Andrew Curran on x
    https://deepmind.google/... Dream Track is a partnership with artists. Examples in the link. [image]
  • @catalinacangea Cătălina Cangea on x
    Beyond thrilled to share my dream project ever since I got into ML! Have been floored by #Lyria so many times - it's simply on another level 🤯 Humbled by the amazing artists supporting our tech in Dream Track and excited to see how Music AI tools boost musical creativity! 🎶❤️🎤