Interactive studio Iconic launched Pressure Point, a demo showcasing AI “Digital Actors” that enables real-time, natural voice interactions with game characters while keeping gameplay within human-authored narrative bounds. The system operates on “directed open-endedness,” driven by a persona blueprint and a narrative blueprint, and executes through a real-time cascade of three AI models: Automatic Speech Recognition (ASR) for transcribing player input and analysing emotional cues; a custom Large Language Model (LLM) engine utilising Gemma 4 for narrative context and dramatic beat generation; and Contextual Text-to-Speech (CTTS) for rendering natural delivery with breaths, pauses, and self-corrections. A key breakthrough is local execution, bypassing external cloud data centres to eliminate network lag and minimise operational costs. The system achieves a median speech-to-speech turnaround time of 1,200 milliseconds (100ms ASR, 700ms LLM processing, and 300ms CTTS generation), with an internal target of bringing latency below one second. The entire inference stack runs alongside Unreal Engine on a single consumer-grade GPU, and asynchronous scheduling moves non-critical LLM background tasks to moments when the player is silent. Industry researchers and game developers highlighted the demo’s naturalistic dialogue and narrative control. Professor Julian Togelius (NYU / Unity Advisory Council) praised local models for removing datacenter round-trip lag, calling it the first time he truly enjoyed interacting with an LLM-driven NPC.