The whole dayThu 19 Nov 2026
AI Compass
WeeklyArchiveAbout

Google opens Genie 4 interactive world model in Gemini API

Available in preview on 19 November 2026 via the v1beta Interactions API and Google AI Studio with real-time 720p WebRTC streaming and 48 kHz stereo audio.

Video: Google

Google opened Genie 4 (models/genie-4) to developers on 19 November 2026 through the v1beta Gemini Interactions API and Google AI Studio, one day after Google DeepMind rolled out Genie 4 in Project Genie. Initialised via a world_setup event from a text prompt, a 16:9 reference image or both, the model streams continuous 1280x720 (720p) environments at 24 frames per second with synchronised 48 kHz stereo audio covering ambient soundscapes, effects and spoken character dialogue, applying SynthID watermarks to every frame.

WebRTC and WebSocket SDK controls, regional latency and per-frame billing

Applications connect through the google-genai Python SDK or @google/genai JavaScript and TypeScript SDK over WebRTC for browser sessions (minting interaction-scoped ephemeral auth_token credentials on the server) or WebSockets for backend pipelines. Native keyboard and camera user_action events (key_w, key_a, key_s, key_d and arrow keys) respond in roughly 0.2 to 0.5 seconds across United States, Western Europe and Japan data centres, whereas mid-session text input prompts pass through Gemini world planning in 1 to 2 seconds to shift weather, lighting or objects live.

Genie 4 requires a paid Gemini API key and bills 240 video output tokens per frame (5,760 tokens per second at 24 fps, or roughly $0.10 per second including stereo audio), with sessions capped at 120 seconds. Because closing a browser tab or calling session.detach() leaves server-side generation running, developers must invoke session.complete() or session.cancel() explicitly to stop billing.

Technical details

Model ID and API surface
models/genie-4 on Gemini Interactions API (v1beta) via WebRTC and WebSocket
Output stream and session cap
1280x720 (16:9) at 24 fps with 48 kHz 16-bit stereo audio; 120-second hard cap
Paid API token billing
240 video output tokens per frame (5,760 tokens/sec, or ~$0.10/sec with audio)
Serving data centre regions
United States, Western Europe and Japan (< 150 ms optimal round-trip latency)

Release details & context

Rolling temporal horizon, SCTP payload limits and model positioning

Unlike persistent 3D scene graphs, Genie 4 simulates a rolling visual horizon: looking away from an object for 8 seconds or rotating 360 degrees can rearrange background landmarks, and stability gradually degrades past 60 to 90 seconds. Initial world setup takes 5 to 9 seconds before frame 1 arrives, and WebRTC SCTP data channels cap control payloads at 64 KB (requiring JPEG reference seeds under 48 KB).

Google’s documentation recommends Genie 4 for playable spatial exploration, Gemini Omni 1.2 Flash for offline 1080p or 4K clips, and Gemini 3.8 Live for bidirectional microphone, camera and tool-calling sessions.

Common questions

Does closing a browser tab stop Genie 4 token billing in the Gemini API?

No, disconnecting a browser socket or exiting an async context detaches the transport without halting server generation, so applications must call session.complete() or session.cancel() to terminate billing.

Does Genie 4 support live microphone input, function calling or 9:16 portrait video?

No, Genie 4 accepts startup text or a 16:9 reference image plus keyboard and mid-session text events at a fixed 1280x720 aspect ratio, without live user audio, camera streams or tool calling.

Google release timeline (40 launches tracked)

  1. Earlier17 Nov 2026
    Google AI Studio adds custom domains and HD Android emulator builds

    Google AI Studio adds direct custom-domain purchasing and hosting alongside HD audio Android emulation, Firestore sync and personal Play publishing.

  2. Earlier18 Nov 2026
    Google launches Gemini 4 Neon at $3 and $15 per million tokens

    Google launches Gemini 4 Neon between Hydrogen and Carbon, ranking first on the Artificial Analysis Coding Agent Index at 58.6.

  3. Earlier18 Nov 2026
    Google Labs unveils Stitch Loop 24/7 product optimisation agent

    Google Labs introduces Stitch Loop, an evergreen post-launch agent that monitors live product metrics and opens sandboxed GitHub pull requests.

  4. Earlier18 Nov 2026
    Google brings re-architected Gemini app to Android Go edition phones

    Google launches a lower-memory build of the Gemini app for eligible Android (Go edition) phones with 45-language Gemini Live voice chat.

Explore the full Google dossier or browse all model releases.

Also in the Thursday 19 November edition

Read all 16 launches on one page
  1. 02
  2. 03
  3. 04
  4. 05
  5. 06
  6. 07
  7. 08
  8. 09
  9. 10
  10. 11
  11. 12
  12. 13
  13. 14
  14. 15
  15. 16

Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X

Email Edition · Early Access

Get the 5-minute AI briefing

Daily and Sunday Weekly inbox editions open soon. Join the early-access list.

Zero spam · Privacy

! Please enter a valid email address (for example, you@domain.com).

Morning Edition Alerts

Get a 1-click alert at 11:00 IST

One quiet browser alert when each daily or Sunday Weekly edition goes live between 11:00 and 12:00 IST. No email required. Privacy