Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.spatius.ai/llms.txt

Use this file to discover all available pages before exploring further.

GitHub Repository

Kotlin + Compose sample implementing the avatar pipeline: VAD → ASR → LLM → TTS → AvatarKit.
This quickstart targets the Direct Mode path on Android. The sample app pastes the Session Token in the UI rather than fetching from a backend — convenient for first-run validation.

​
Prerequisites

  • Android Studio (latest stable)
  • JDK 17
  • Android API 24+ device or emulator (arm64-v8a, real device recommended)
  • Spatius credentials. See Credentials.
  • An OpenAI API key for the ASR + LLM + TTS pipeline used by the sample.

​
Run it

1

Clone and configure

git clone https://github.com/spatius-ai/spatius-avatar-demo.git
cd spatius-avatar-demo/direct-mode/clients/android
cp local.properties.example local.properties
Fill local.properties:
SPATIUS_APP_ID=<your-app-id>
SPATIUS_AVATAR_ID=<your-avatar-id>
OPENAI_API_KEY=<your-openai-api-key>
OPENAI_USE_PROXY=false
Session Token is not configured in files — paste it in the app UI at runtime.
2

Build

JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home" ./gradlew :app:assembleDebug
Install with Android Studio or adb install.
3

Start a conversation

In the running app:
  1. Initialize the avatar.
  2. Paste your Session Token.
  3. Tap Start Conversation.
  4. Speak and pause to trigger a round.

​
What this validates

CheckWhat it tells you
Avatar rendersApp ID + Avatar ID are correct, Maven dependency resolved.
Conversation startsSession Token is valid, Motion Server connection works.
Avatar speaksFull pipeline (mic → ASR → LLM → TTS → AvatarKit) is wired up end to end.

​
Next steps

Android SDK reference

Complete Android API documentation.

Browse all demos

Web (multi-framework) and iOS samples in addition to Android.