The Guide walks you through integrating SpatialReal avatars by integration mode. Choose the mode that matches your architecture, then follow the linked guides for your platform (Web, iOS, Android) or backend (LiveKit, Server SDK).Documentation Index
Fetch the complete documentation index at: https://docs.spatialreal.ai/llms.txt
Use this file to discover all available pages before exploring further.
Integration Modes
SDK Mode
Client sends audio; SDK handles networking and rendering. Best for simple, client-centric apps.
RTC Mode & Framework Plugins
Real-time voice via LiveKit. Use framework plugins or Server SDK with egress.
Host Mode
You control the transport. Server SDK sends audio and relays animation to the client SDK.
Agent Mode
Fully managed voice agent (coming soon).
Where to Start
- New to SpatialReal? Start with Overview → Speech-to-Avatar Quickstart, then open the guide for your chosen mode.
- Already chose a mode? Use the sidebar: pick SDK Mode, RTC Mode, or Host Mode, then follow the platform-specific quickstarts (Web, iOS, Android) or server guides (LiveKit).
- Want working code? Check out our Demo Projects for complete examples you can run immediately.
Quickstart Code Walkthroughs
Speech-to-Avatar Walkthrough
Understand the SDK Mode quickstart code structure and runtime flow.
Agent Quickstart Walkthrough
Understand the LiveKit agent quickstart backend and frontend architecture.
AvatarKit Voice Agent Demo
A full reference repository with implementation details, including different frontend UI options and multiple backend agent patterns.