SSyncDev

Genie 4

SyncDev model directory · Profile updated Nov 19, 2026

Compare with another model

Genie 4 is Google DeepMind's interactive world model with real-time native audio, available in Project Genie to eligible Google AI Ultra subscribers.

Key specifications

Specification score
10.0
License
proprietary

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: No API or per-use price; access comes with a Google AI Ultra subscription via Project Genie.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input

Produces

  • Video output
  • Audio output

Capabilities

Audio

What is Genie 4?

Most generative video ends when the clip does. Genie 4 does not hand you a clip at all: it builds a world you walk around in, live, in the browser, and keeps building it as you move.

Google DeepMind released it on 18 November 2026 inside Project Genie, the Google Labs experiment at labs.google/projectgenie. It is a world model, and Google describes it as its most realistic and interactive one so far.

Who gets to use it

Access is narrow, and it is worth being plain about that:

  • Google AI Ultra subscribers who are eligible receive it in a rollout that began on 18 November.
  • Google AI Pro members can join a waitlist.
  • Developers have no API to call. Nothing in the release mentions one, and there is no per-request or per-token price; access comes bundled with the subscription.

So, if you came here hoping to wire it into a product, the honest answer today is that you cannot. You can explore what it does, and judge whether it is worth tracking.

What changed from Genie 3

The big addition is sound. Genie 4 is the first Genie model to generate real-time native audio alongside its visuals, and that audio adapts to the scene, ranging from ambient soundscapes up to character dialogue. Visual fidelity and physics are also pitched as the best the series has offered.

You steer with text. A prompt starts the world, and further prompts mid-session alter it while you are inside, changing the weather, adding characters, or triggering actions.

Genie 3 has not gone away. It stays in Project Genie's model picker and picked up upgrades of its own: sessions now run three minutes per generation instead of sixty seconds, worlds can be chained into longer journeys, a 360-degree panorama can seed a world, and natural-language prompts can trigger in-world events.

Tools around the model

  • A Project Genie agent that assembles worlds from a conversation, orchestrating several multimodal models and composing a background score.
  • Gemini watching the session, suggesting where to go next or triggering events.
  • A community gallery for publishing, exploring and remixing other people's worlds.

Every piece of video and audio from Project Genie is marked with SynthID.

Known rough edges

Google lists four open research problems: camera latency, intricate physical interactions, precision in the real-time audio, and keeping a scene consistent over long stretches. Expect objects you walked past to drift if you come back later.

No resolution, frame rate or session cap specific to Genie 4 has been published, so we have left those out rather than guess.

How to judge it in an hour

Pick a single scenario you care about, say a training environment, a game prototype or a pitch walkthrough. Then run it twice, once on each generation, using the same prompt. Watch three things: whether the audio actually matches what is on screen, how quickly the camera responds to input, and whether a landmark you leave is still the same when you return. That last test exposes the persistence limit faster than anything else.

If you need rendered clips for a pipeline rather than an explorable space, a conventional text-to-video model such as Veo 3.1 remains the practical choice, since it has developer access. The rest of Google's lineup sits on the Google provider page.

How to evaluate Genie 4

Compare the model on the work you need to complete.

Tasks and inputs

Genie 4 is listed for Multimodal, Text-to-video. It accepts text and produces video, audio. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Choose duration, resolution and frame rate together. Compare the cost of an accepted clip, including repeat generations.

Choosing a deployment

Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.

Frequently asked questions

Eligible Google AI Ultra subscribers in Project Genie, in a rollout that began on 18 November 2026. Google AI Pro members can join a waitlist.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

Apple

FastFrames-L

FastFrames-L is Apple's open 14B autoregressive two-step video diffusion model that generates 480p video at interactive latency, distilled from Wan2.1-14B.

— context

Google

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash is Google's conversational video generation and editing model, making 3-15 second clips with native audio from 360p to 4K.

131.07K context

pika

Pika H3 Flex

Pika H3 Flex is Pika's open LoRA post-training of MiniMax H3: six-step sampling, up to 15 s clips with 32 kHz stereo audio at 480p or 768p, 24 fps.

— context

Tencent

Hy-Nomas

Hy-Nomas is Tencent Hunyuan's open interactive world model: it generates 720p video segment by segment, steered by text and camera controls.

— context

heygen

HeyGen Video 1

HeyGen Video 1 generates 5 to 30 second MP4 clips with audio from text, images or reference media, up to 2K at 24 fps. Built on MiniMax H3.

— context

Meta

Muse Video

Muse Video is Meta’s previewed video-generation model with native audio; a public Meta Model API route and price have not been established.

— context