Realtime session API
Spin up a digital human session with vision, audio, and speech in one handshake.
Loading
Loading
Developers
APIs for perception, voice, rendering, and cognition. Request access and we’ll get you set up.
Request API accessSpin up a digital human session with vision, audio, and speech in one handshake.
Subscribe to gaze, emotion, and scene events as structured signals.
Stream TTS with facial animation channels for your client renderer.
Hook memory, retrieval, and tool calls into your own backends.