Immersive

When AI becomes
animated.

A face that looks back, blinks, and answers out loud. The character you chose takes the floor, lips in sync with the words, in 80 languages.

See it in a room

A new exhibit

It becomes part of your collection.

Not a tool bolted onto the visit. A stop on the route, with its own place in the room, that visitors queue for, talk about on the way out, and come back to see.

Press coverage, school bookings, returning families: an avatar is programming, and it earns its line in the season like any other exhibit.

A point of interest in its own right, with a place in the visitor route
Something to announce: a launch, a press angle, a reason to return
Animated avatar with lip-sync, answering out loud in real time
Every spoken answer also written on screen, for anyone who cannot hear it

Vénus d'ArlesDeployed on a screen in the room, with headphones and a bench. The visitor sits down and talks.

How it works

You bring a face, or just an intention.

We take it from there. You will not be asked to produce artwork, rig a model or write a technical brief.

What you bring

A morning of your time

An existing image if you have one, or simply the figure you have in mind. Plus the sources the character will draw on: catalogue entries, archives, scholarly notes.

What we build

Character, animation, voice

The face, the movement, the lip-sync, the register and the refusals. Any style you want: flat 2D, 3D, photoreal, or drawn in the hand of your own illustrator.

How it lands in the room

With your scenographers

We work alongside your exhibition designers on the siting, the acoustics and the hardware, and we hand over the technical specifications they need.

Where it lives

A presence in the room.

A screen, a handset and somewhere to sit, so the exchange feels like meeting someone rather than using a machine. Sited with your designers, wired in, and left alone to work.

Kiosk or wall screen, built into the scenography
Multilingual, with the character held identical in every language
Same profiles as the other levels: default, family, accessibility
If you want it, a QR code opens the same character on the visitor's phone

A physical Ask Mona totem in a dark room: a portrait screen showing Dorothea Herbert, with a handset and a framed sign on the wall — **Carrick-on-Suir**The totem and its handset, sited with the museum's own designers.

A school group standing in a dark museum room in front of a large lit screen showing a classical head

Built for the room

It has to survive a school group.

Fixed screen, wired handset, no login, nothing to break. A visitor picks it up, talks, hangs up, and the next one starts fresh.

Field results

An avatar is not a gadget if it holds the visitor.

0more engagement than a conventional mobile appChâteau de Versailles, 20 statues and fountains, OpenAI Realtime

0average time in front of an equipped work, against five seconds beforeMNBAQ, 50 works equipped

0languages available, with the same character in each19 confirmed in production to date

The foundation

The same engine and the same console behind all three levels.

Essential, Enhanced and Immersive change what the visitor sees. What answers, and what you steer it with, never changes. Follow one question through it.

Your sourcesYou load

The knowledge baseYou edit

The engineIt answers

The evaluatorIt checks

The visitorIt speaks

And it comes back to you. Every conversation turns into structured data in the console: what audiences asked, what they failed to find, when, and in which language.

Your sources

Whatever you already have, in the format it already exists. Nothing to rewrite for the machine.

PDF and Word
Web pages
Spreadsheets
Images
Your collection database

The knowledge base

The console is yours. Change an answer, publish it, and see the result immediately, with no developer in the loop.

Edit and publish yourself
Preview and test instantly
One base, all three levels
No technical skill required

The engine

Several models under one orchestration layer, tied to no single provider. It answers from your sources and nothing else.

Only what you approved
No provider lock-in
Visual recognition on request
A work identified from a photograph

The evaluator

Every answer is scored before it reaches anyone, in each of the languages you serve.

Faithfulness to your sources
Tone
Safety
Scored in every language

The visitor

They ask in their own words and get your answer, in the character you approved, out loud and on screen.

Voice and text together
80 languages
Same character in each
Nothing to download

Next step

Give one work a voice, and see what happens.

Pick a single piece, send us its file. We come back with a character you can talk to, and the transcript of everything visitors asked it.

Book a demo

When AI becomesanimated.