Spatius launches real-time AI avatar layer: give any voice agent a face at $0.42/hour
HeyToha · x · 2026-11-02
Startup Spatius launched AvatarKit, a real-time AI avatar infrastructure that turns any voice AI agent into a talking avatar with synchronized lip movements, starting at $0.42 per avatar hour and testable in 10 minutes.
How it works: you bring your own audio → a compact expression/timing control stream is sent → the face renders on-device, avoiding continuous cloud-video costs. It ships across Web, iOS, Android, kiosks, and embedded devices.
Hands-on flow (the author posted a step-by-step tutorial):
- Create a custom avatar in Spatius Studio from an uploaded image; generation takes 3–5 hours
- Tune expressiveness, head, and jaw settings in Studio
- Integrate via Direct Mode or Backend Mode depending on your audio/conversation architecture
- Keep server-side API keys secret and follow the documented secure session flow
The author demoed making an Einstein avatar talk, and suggests use cases like face-to-face AI doctors, real-time tutors, expressive voice assistants, and customer support agents.
Related event: Spatius Launches Real-Time AI Avatar Layer Starting at $0.42/Hour(2 posts)→
More from coding & agent
- Pinokio Update Brings "Remote AI": Control Local AI Apps From Anywhere — cocktailpeanut · 2026-11-03
- Flock: A New iOS App for Running AI Coding Agents, Built on a t3code Fork — seatedro · 2026-11-03
- WhatIf: 10,000+ steerable LLM agents form a flight simulator for policy — scyrusk · 2026-11-03
- LLMs solving math gets all the hype, but their new infrastructure patterns for reliable software go unnoticed — StewartalsopIII · 2026-11-03
- Vibe coding's 5-year leap: from a GPT-3 React button demo to an Opus 5.5 three.js world — bennash · 2026-11-03
- Stripe's Link Agent Wallet lands in Merge Agent Handler: agents pay without seeing card details — shensi · 2026-11-03