SpatialReal currently provides avatar-only services, focusing on generating and rendering real-time avatar animations based on audio input. Voice conversation logic, speech synthesis, and other agent functionalities are managed by your application or third-party services.
1) Compare Integration Modes
| Mode | Characteristic | Latency | Dev Effort | Ideal Scenario |
|---|---|---|---|---|
| SDK Mode | Client-centric | Moderate ⏱️ | Low 🟢 | Easy client-centric integration. |
| Framework Plugin | Voice agent framework plugin | Ultra-Low ⚡ | Low 🟢 | Use LiveKit Agents or TEN Framework. |
| RTC Mode | Transport via Agora/LiveKit | Ultra-Low ⚡ | Medium 🟡 | You want to optimize latency, and use LiveKit or Agora as transport layer |
| Host Mode | Use your own transport layer | Low 💨 | High 🔴 | Full control over data transport. |
2) Start from Runnable Examples
AvatarKit Voice Agent Demo
A collection of example projects that can work out of the box after API keys are filled in
.env.3) Guides
SDK Mode Guide
Start with client-centric integration.
Host Mode Guide
Build custom transport and server orchestration.
RTC Mode & Framework Plugin Guide
Use LiveKit or Agora for real-time delivery, including LiveKit Agents and TEN Framework integration.