Human AI Agents have a real face and a real voice, and run live conversation rather than turn-based exchange. Interrupt mid-sentence, trail off, talk over it, and the endpointing holds.

Setup is one still photo, a persona and a voice. No rig, no capture session, no script.

Two face models sit behind a single API. Portrait is built for speed and scale, Presence for expressiveness. Both stream over WebSocket and drop into Pipecat, LiveKit, or your own pipeline. Python and TypeScript SDKs are open source.