AI Human Web SDK v2

Add a real‑time, talking AI avatar to any web page with a single script. The v2 SDK streams a 2D avatar that speaks your text (or LLM responses) with natural lip‑sync — no video pipeline, no plugins.

Beta

Web SDK v2 is in beta. The core API is stable and mirrors the v1 AIPlayer class; newer options (see Configuration) are still being finalized. For the current stable release, see Web SDK v1.

Talk to AI Human

Try it live — type a message and the avatar speaks it back with real‑time lip‑sync. This demo runs on the published SDK exactly as you would integrate it.

Why v2

• Drop‑in. One <script> tag exposes the AIPlayer class — new AIPlayer(el) and go.
• Real‑time speech. Send text and the avatar speaks it back with lip‑sync, streaming.
• Smoother playback. Optional continuousBackground removes the background jump when speech starts; enableEarlyStart shows the avatar sooner.
• Mobile‑optimized automatically. On phones the SDK trims the idle background download so the avatar appears faster — no code change required.
• Familiar API. The core AIPlayer class mirrors v1 — most calls carry over. (3D and custom‑voice APIs are removed; see the comparison below.)

How it works

What's different from v1

	Web SDK v1	Web SDK v2
Rendering	2D / 3D	2D only
Distribution	aiPlayer-1.6.x.min.js	aiPlayer-2.x.obf.js
Background continuity	—	continuousBackground (beta)
Faster first render	—	enableEarlyStart (beta)
Mobile idle download	full	auto‑trimmed
API surface	AIPlayer class	same AIPlayer class

Next steps

Getting Started →

From empty HTML to first speech.

Configuration →

Options and tuning.

AIPlayer API →

Full method and callback reference.