SpAItial AI

Large, consistent, and high-quality 3D worlds from simple iPhone recordings. Works for multi-room scenes, fills missing gaps consistently while maintaining high quality, and it’s super easy to use. Now in beta with partners and coming soon to the SpAItial API. Link to the scenes are in the comments so you can explore these world yourself 👇

Real-world capture is almost never complete. A missed corner, object, a room that didn't get enough viewpoints etc. leaving empty holes where the geometry should be. Our SOTA model Echo is built for that reality. It fills unscanned regions from surrounding visual context, so you still get a complete, explorable 3D world instead of broken voids. Incomplete capture shouldn't mean an incomplete experience.

Our SOTA world model, Echo, reconstructs high-quality scenes from sparse inputs and fills missing areas using its world knowledge. That means far less capture, data, and prep to produce geometrically consistent, multi-room reconstructions. We can’t wait to share it. Public release coming soon

SpAItial AI is building the next generation of world models, and they’re hiring a Chief of Staff alongside technical roles in London and Munich. Founded out of deep research at TU Munich, SpAItial is moving generative AI beyond 2D pixels toward models that understand the physics and geometry of the real world. With Echo-2, the team recently showed how text or image inputs can become spatially consistent 3D worlds, explorable in real time. Since backing SpAItial’s $13 million Seed round last year, we’ve watched Matthias, Luke, Ricardo, David, and the team push an entirely new AI category forward from Europe. They’re now hiring across company-building, research, and engineering roles, with real ownership over how this new AI category is built and scaled. Open roles linked in the comments.

Announcing the SpAItial Startup and Creative Partners Program for teams and creators building with world models. Accepted applicants get free credits, priority API access, early Echo model access, integration support, a direct feedback loop with the lab. We want real builders using Echo in real workflows so your feedback shapes what comes next. Apply here: Startup Program https://lnkd.in/eQ9NnznW Creative Partners https://lnkd.in/euhQukuP We are accepting applications on a rolling basis.

Sparse captures in, complete worlds out. Echo reconstructs scenes from a small set of views, using world modeling priors to fill what sparse 3DGS leaves behind. Coming soon to the SpAItial API.

New from SpAItial. You can now: ➡️ Create 3D worlds directly from the Claude desktop app via our plugin ➡️ Create with your agents using the SpAItial AI MCP server. Works for Claude Code, Codex, Cursor, OpenCode, VS Code etc Create, edit, refine your worlds without leaving your chat! See links in the comments 👇

SpAItial ❤️ CVPR'26 We're hosting a welcome event tonight, Wed June 3d 6pm-9pm, and welcome you to CVPR on the first day of the conference! Come meet the team and get a first look at Echo-2, our latest physically-grounded world model. We'll have plenty of drinks, dinner, and great conversations. Bring your A-game: Make sure to brush up on your Quake 3 skills, as we’ll be hosting matches on custom maps generated live by our AI. We’ll also have two bocce courts up and running if you want to test your real-world physics skills between beers! We run an open waitlist, until we reach capacity. Register here: https://luma.com/7xw151m9

SplatArena: Multiplayer arena is LIVE 🚀🚀🚀 Quake3-style combat. Drop in, frag your friends, and play on a world generated by Echo-2. Play now, directly in your browser: https://arena.spaitial.io

Releasing Echo-2 HQ, an improved model that delivers greater detail and sharper results. You can zoom in super close and discover remarkable appearance fidelity. Available via API and in the app. Try it out! Check out some of the scenes below👇