← Back
Google DeepMind

Genie 4 is now available

•6 min read•
#llm#agents
Genie 4 is now available
Level:Advanced
For:AI Engineers
✦TL;DR

Genie 4 launches for Google AI Ultra subscribers, delivering the most realistic and interactive world model yet with real‑time text‑prompted environment edits and native audio that adapts on‑the‑fly. The update also adds Genie 3 enhancements—sessions up to 3 minutes, 360° panorama grounding, and linked world sequences—for longer, panoramic experiences. Engineers can now embed conversational world‑building via the new Project Genie agent and share creations through a community gallery, opening new avenues for AI‑driven immersive content pipelines.

⚡ Key Takeaways

  • Genie 4 enables real‑time environment editing via natural‑language prompts and streams adaptive native audio.
  • Genie 3 now supports up to 3 minutes per generation (up from 60 seconds) and 360° panorama‑seeded world grounding.
  • World chaining lets multiple generated worlds be linked for extended journeys.
  • The Project Genie agent assists users in building custom worlds through simple conversational interactions.
  • Published worlds can be shared, explored, and remixed in a community gallery.
💡 Why It Matters

Real‑time, promptable world generation with audio lets engineers create dynamic immersive experiences without pre‑rendered assets, accelerating prototyping and user‑generated content loops.

✅ Practical Steps

  1. Access Genie 4 by logging into the Project Genie website as a Google AI Ultra subscriber and select the Genie 4 model in the model picker.
  2. Use natural‑language prompts during navigation to modify weather, add characters, or trigger events, and observe native audio adapting in real time.
  3. Publish your generated world via the community gallery to enable remixing and discovery by other users.

Want the full story? Read the original article.

Read on Google DeepMind ↗

More like this

Censored vs. Truncated Regression in Python, Explained

Towards Data Science•#llm

New in AWS Quick: More capable flows, an updated web experience, and agents that work together

AWS ML Blog•#agents

How Google Duplex evolved to also call businesses for you in Gemini

Google Research•#agents

Q&A: Enabling more human-like interactions and understanding in multimodal foundation models

MIT News AI•#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING