GitHub Repository
SwiftUI sample implementing the avatar pipeline: VAD → ASR → LLM → TTS → AvatarKit.
Prerequisites
- Xcode 16+
- iOS 16+ device or simulator (real device recommended for mic input)
- Spatius credentials. See Credentials.
- App ID — from Spatius Studio
- Avatar ID — from the Avatar Library
- Session Token — see Session token API
- An OpenAI API key for the ASR + LLM + TTS pipeline used by the sample.
Run it
1
Clone and open the sample
2
Configure credentials
Edit
AvatarDemo/Config.swift:Session Token is not stored in Config.swift — paste it in the app UI at runtime.3
Build and run
Use Xcode to build and run on a connected iOS device or simulator. The
AvatarKit.xcframework is downloaded automatically on first build from the configured release.4
Start a conversation
In the running app:
- Paste your Session Token.
- Tap Start Conversation.
- Speak and pause. The avatar should respond with lip-synced speech.
What this validates
Next steps
iOS SDK reference
Complete iOS API documentation.
Browse all demos
Web (multi-framework) and Android samples in addition to iOS.

