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

Minimal Web Direct Mode demo. Streams prerecorded PCM audio and renders the lip-synced avatar.
This quickstart targets the Direct Mode path. No agent backend or LiveKit setup needed — just credentials.

​
Prerequisites

​
Run it

1

Clone the repo and enter the quickstart folder

git clone https://github.com/spatius-ai/spatius-avatar-demo.git
cd spatius-avatar-demo/direct-mode/clients/web/speech-to-avatar-quickstart
2

Install dependencies

pnpm install
3

Create your .env

cp .env.example .env
Fill VITE_SPATIUS_APP_ID, VITE_SPATIUS_AVATAR_ID, and VITE_SPATIUS_SESSION_TOKEN.
4

Run the dev server

pnpm dev
5

Open the demo

Open http://localhost:3000, click Connect Avatar, then Send Audio. The avatar should load, connect to Motion Server, and play the demo audio with lip sync.

​
What this validates

CheckWhat it tells you
Avatar loadsApp ID + Avatar ID are correct, asset CDN reachable.
Connect button succeedsSession Token is valid, Motion Server connection works.
Audio plays with lip syncPCM audio format and rendering pipeline are wired up end to end.

​
Next steps

Direct Mode guide

Full Web SDK integration with your own audio source.

Browse all demos

Multi-framework Web references (React / Vue / Vanilla / Next.js) plus iOS, Android, and Flutter.