NewMedia Creative Technology Studio combined a large LED character, directional voice capture and remotely hosted AI processing for AI HOST, its interactive installation at IMEX America 2026. The system brought several stages of speech processing and character animation into a public conversation, with the studio reporting a median of 2.6 seconds between a visitor’s last word and the start of the character’s reply.
The installation at the company’s stand used a 6 ft wide by 12 ft high LED wall, approximately 1.83 by 3.66 meters, built with AOTO RM1.5E panels and driven by Brompton processing. NewMedia specifies the panels at 1,500 nits, with Mini 4-in-1 LED technology, 1/16 scan and a 7,680 Hz refresh rate.
A 12.9-inch iPad ran a touchscreen interface developed in-house. Visitors selected one of four characters, entered their name and started speaking through an Audio-Technica PRO49QL gooseneck microphone. A JBL stereo system reproduced the character’s voice, while facial animation and lip-sync gave the generated response a visual performance on the LED wall.
Voice capture was a central part of the installation design. The team used a directional microphone and configured volume-threshold gates to manage ambient exhibition noise. The input had to remain usable for speech recognition while the character’s reply was played into the same public environment.
The on-site show computer was a custom laptop equipped with a 24-core Intel Core Ultra 9 275HX processor and an NVIDIA GeForce RTX 5090 Laptop GPU with 24 GB of GDDR7 memory. Its configuration included 96 GB of DDR5 memory and a 4 TB PCIe Gen 5 SSD. External liquid cooling formed part of the laptop setup.
The show computer ran Unreal Engine 5 for real-time facial animation and lip-sync, with a specified frame rate of 60 fps. This was paired with NewMedia’s own AI infrastructure in a data center in Spain, accessible to the team remotely.
The studio’s dedicated AI server specification lists eight NVIDIA RTX PRO 6000 Blackwell GPUs with 768 GB of combined GPU memory, dual AMD EPYC server processors and 1 TB of ECC system memory. Enterprise NVMe storage completes the server configuration.
Diego De Anna, NewMedia’s founder and CEO, describes a software workflow linking speech-to-text, understanding, response generation, splitting, voice generation, animation and lip-sync. The processes are coordinated so that the character can begin delivering an answer as it is generated.
“The system does not wait for the complete answer before it begins speaking, which is why the response feels so immediate,” says De Anna.
Connectivity was addressed through a local fallback alongside the remotely hosted processes. NewMedia reports four internet interruptions during the presentation, covered by offline voice support.
“The application includes prerecorded answers and animations, as well as smaller models that can run locally,” says De Anna.
The production also required decisions about how a character should perform during an unpredictable exchange. Carolina Comas García, executive creative director, says the team combined a wide range of animations with gate logic and artistic direction to make the character adaptable to the live situation. The installation was delivered as a live-operated experience.
The four roles gave that system different conversational tasks. NewMedia Guru discussed the company and the events industry; The Quiz Master ran quizzes on a chosen subject and difficulty level; The Compliment Machine offered a playful exchange; and The Oracle provided fictional predictions. Spoken answers were accompanied by live subtitles.
According to the studio’s system records, 329 individual visitors took part in 402 conversations across Smart Monday and the three show days, October 13–15. Some visitors spoke with several characters. Interactions took place in English and 25 other languages, and 99% of visitor exchanges were spoken aloud.
AI HOST was developed by the NewMedia team, including Comas García, De Anna, Camilo De Anna and Adrien Boitelle. Its brand-specific commissions combine character design, conversation settings, animation and show logic with the hardware and operation required for the venue. The client supplies the brand brief and reference information, and approves the character and voice.
