Architects, creators and robotics teams wanting explorable 3D scenes from a single image, though pricing hasn't been published.
Kenning's take
What it does
Echo-2 is a world model from SpAItial that generates a 3D scene from one image or a text prompt. Unlike video models, it produces a consistent 3D representation that can be explored and rendered in real time on any device. SpAItial pitches it for digital twins of real spaces, architecture, robot training and 3D content.
- 3D worlds from a single image or text prompt
- Spatially consistent scene, not a video
- Real-time rendering in the browser on any device
- Available through an app and an API
Who it suits. Creators, architects and robotics teams who need explorable 3D scenes.
Key facts
- Category
- AI models
- Made by
- SpAItial Ltd.
- Released
- 28 April 2026
- How to get it
- through the SpAItial app ("Try Echo") and API
- Works on
- Web, API
FAQ
When was Echo-2 released?
SpAItial announced Echo-2 on 28 April 2026.
What does Echo-2 make?
An explorable 3D scene from a single image or a text prompt, which renders in real time.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.
Cisco Antares
Cisco's small open-weight models that find where known security vulnerabilities sit in a codebase, running locally.