Real Personalities. Brought to Life.
AI-powered Digital Humans your visitors can talk to.
For culture, education, entertainment and brands.
Seen.Heard.Remembered.
AI Digital Humans with knowledge you control.
Bring your artworks, historical characters, experts, brand characters, and exhibition personalities to life as interactive, emotional experiences. You decide what they know, how they speak, and what they won’t answer.
Every conversation is unique.
Every experience becomes a living memory.
Not a chatbot on a screen
Talking Paintings is a character experience built for physical spaces: exhibitions, attractions, showrooms and public installations.
What Talking Paintings is
- A 3D character that reacts in real time
- Real voice, movement, personality and curated knowledge
- Knowledge prepared for your project, for accurate answers
- A content-controlled format approved by your team
Talking Paintings doesn't replace your existing information or personal guidance. It adds a dialogue-based layer to selected stories, so people can find their own way in.
Real characters, real institutions.
Alan Turing
Museum für Kommunikation Frankfurt. Shortlisted for the DigAMus Award 2026.
Read the Case Study →
Joseph Haydn
Schloss Esterházy and Burg Forchtenstein. A Talking Paintings Lite character.
Read the Case Study →
Prince Esterházy
Schloss Esterházy, Eisenstadt. Shares his own family history with visitors today.
Read the Case Study →
Vincent van Gogh
Created for “Vincent: Between Madness & Wonder” by Alegria Exhibition.
Read the Case Study →
Alfred for MERCK
A Digital Human brand host. Created once and used in Darmstadt and South Korea.
Read the Case Study →
Give visitors a reason to come back and a story to tell when they leave.
A clear invitation
Visitors receive a clear invitation, for example: “What would you like to know about me?”
Greeting
The digital avatar greets visitors with voice, presence, and subtle movement.
Asking questions
Visitors ask questions by voice or text input. Depending on age, background, and interest, visitors can ask simple, personal, multilingual, or detailed questions.
Real-time response
The character responds in real time, based on the approved knowledge base and with its defined personality and tone.
Going deeper
Visitors can ask follow-up questions, switch languages, or explore related topics.
Evaluation
Your team can review frequently asked questions and use these insights to improve interpretation, signage, education material or brand messaging.
Result: Talking Paintings gives audiences a memorable and engaging interaction.
Different ways to bring a character to life
Prepared storytelling with Lite, guided choices with Lite Plus, open conversation with AI, or a ready-made character to rent. On framed displays, kiosks, projections or exhibition installations.
Watch the character come to life
The character delivers pre-produced animated storytelling. No visitor input needed.
Best for: Storytelling, atmospheric installations, eye-catching character moments
Choose what the character talks about
Visitors pick from prepared questions or topics on a touchscreen, button or menu. Each choice plays a prepared answer.
Best for: Guided interaction, curated stories, reliable visitor journeys
Have a real conversation
Visitors ask their own questions. The character understands, answers in real time from approved knowledge and keeps the conversation going, in 32+ languages.
Best for: Open exploration, Q&A, multilingual dialogue, deeper engagement
A ready-to-use character
An existing character from our library for temporary use, including software, standard hardware and setup.
Best for: Temporary exhibitions, events, pop-ups, trade fairs and short-term activations
Adaptable across industries
Museums & Cultural Institutions
Turn a collection into a conversation. Visitors meet artists, historical characters, scientists, experts or other characters connected to your exhibition.
Your curatorial and education teams decide what the character communicates and how the experience fits the exhibition.
Good fit for: museums, galleries, heritage sites, science centres, archives.
Attractions & Entertainment
Create a character guests want to meet. Talking Paintings adds animated storytelling or real conversation to the visitor experience.
The character can work as a standalone installation or as part of a larger visitor experience.
Good fit for: theme parks, immersive exhibitions, touring shows, live events and visitor centres.
Brands & Corporate Experiences
Let people interact directly with your brand. A character can explain products, introduce company topics, present research or host an event or showroom.
Content and communication are prepared around your brand language and approved company information.
Good fit for: brands, trade fairs, corporate events, showrooms, workplaces.
Education & Public Spaces
Give people a simple way to explore a topic. A character can act as an expert, guide, teacher or historical figure.
People listen to prepared stories, choose topics or ask questions in their own words, depending on the format.
Good fit for: schools, universities, libraries, education centres, airports.
Run offline or online? Both are possible.
Choose where Talking Paintings AI does its thinking. The character always runs on local hardware in your space.
- Privacy firstVisitor conversations are processed locally on the installation computer. Visitor text is not stored by default.
- No token costsA one-time investment in hardware and software, with no token or API charges, however many visitors you welcome.
- Fast on-site performanceLocal hardware keeps answers quick, even on your busiest days.
- Stable operationRuns without an internet connection and starts automatically when switched on.
Best for organisations focused on on-site visitors, permanent installations and strict data protection requirements.
- Leading AI modelsConnect to leading cloud-based AI models or connect your own language model.
- Premium cloud voicesUse high-quality cloud voice models or connect your own voice model for natural, expressive speech.
- Connect what you already useIf you already work with a chatbot, its knowledge base can be connected, with data flows documented in the project.
- Lower upfront investmentHybrid installations have up to 50% lower system requirements, reducing the initial hardware investment.
Best for changing exhibitions, touring installations and international audiences that want the newest AI capabilities.
What can Talking Paintings do?
Everything a character needs to hold a real conversation in a real space, and everything your team needs to keep it accurate after launch.
Natural conversation
Greetings, thinking sounds, gentle nudges and follow-up questions make the conversation feel natural, not scripted.
Realistic animation
The character moves in sync with its speech, with facial expression and lip sync that make it feel alive.
Flexible knowledge base
Knowledge is adapted to your exhibition, topic, audience and curatorial guidelines.
Character Editor
Your team adds facts, uploads documents (PDF, DOCX, TXT, MD) and adjusts behaviour in a browser tool. No programming, no new production round.
32+ languages
Talking Paintings AI supports more than 32 languages which can be individually ordered. Visitors can switch chosen languages during a conversation
Custom voice
Real voice direction, and a custom voice clone on request. Names and places are tuned so they are pronounced correctly.
Computer vision
Eye contact and reactions based on visitor presence and movement. It does not identify people, and can be switched off.
Push-to-talk
A talk button next to the microphone keeps conversations reliable in loud museums, fairs and foyers.
Offline & online
Runs on site (On-Premise) or with selected cloud services (Hybrid), depending on your requirements.
API connection
Connect the knowledge base of an existing chatbot you already use, with data flows documented.
Insights
On request, see which topics visitors ask about most. Logging is only switched on by agreement.
Easy daily operation
Starts automatically when switched on, with hidden staff controls and an operator manual for your team.
How we work with you
- 01 / SOURCE MATERIAL
Gathering core knowledge
Identifying data: object texts, catalogs, archives, books, letters, biographies, research, images, timelines, FAQs and educational or brand material.
- 02 / CHARACTER CONCEPT
Defining identity and voice
Role, voice, personality, tone, target audiences, languages, and rules for sensitive topics.
- 03 / KNOWLEDGE BASE & BOUNDARIES
Setting boundaries and approvals
Approved content, fallback responses, restricted topics and approval processes.
- 04 / PROTOTYPE
Testing facts and tone
An initial test version to check facts, tone, dialogue quality and visitor comprehension.
- 05 / HYPERCARE PHASE
Optimizing visitor experience
Testing speech recognition, response speed, voice, animation, hardware, signage, audio and visitor flow.
- 06 / LAUNCH & SUPPORT
Ongoing operations and updates
Maintenance, software updates, content updates, language expansions and new characters.
Open conversation, with clear boundaries.
Every space needs a clear, secure approach to data. Technical, organisational and legal requirements are addressed early, together with your data protection and IT team.
On-Premise option
Voice and interaction data can be processed locally and offline, with no dependence on external cloud services.
Hybrid option
Use selected cloud services only where you approve them. Every provider and data flow is documented in the project.
Optional sensors
Camera, computer vision and sensor functions can be left out completely.
Clear rules
Data retention, analytics, logging and access rights are agreed with you before launch. Visitor text is not stored by default.
Verified knowledge base
Answers come from a closed, approved knowledge source, not the open internet. The character never trains on what visitors say.
Defined fallback behaviour
Clear response rules for uncertain, sensitive or off-topic questions.
In the news
Click any logo to read or watch the original coverage.
Why organisations choose us
10+
Years of expertise
Immersive media, real-time 3D, XR, virtual reality and interactive storytelling.
Awards
Proven projects
Award-winning work such as Mona Lisa's Secret and The Garden of Earthly Delights VR.
100+
Real-world scale
Large and small projects and workshops in museums, attractions and companies across Europe and Asia.
R&D
Funded research
Supported by the Hessian Distr@l programme for developing and testing Talking Paintings technology.
Common questions
Short answers to what institutions, attractions and brands ask us most.
Read all FAQsWhat is Talking Paintings?
Talking Paintings brings artworks and characters to life through animation, voice and interaction. Lite uses prepared storytelling, Lite Plus adds guided choices, and AI allows open, real-time conversations.
Can we control what the character says?
Yes. With Lite and Lite Plus, every word is prepared and approved before launch. With AI, your team defines the approved knowledge, communication rules, tone and restricted topics, and can update facts and documents after launch in the Character Editor.
How many languages does Talking Paintings support?
Talking Paintings AI supports more than 32 languages, and visitors can switch languages during a conversation. Lite and Lite Plus support the languages prepared during production.
Is Talking Paintings only for museums?
No. It works in museums, galleries, exhibitions, attractions, trade fairs, showrooms, company events, schools, universities, libraries, airports and public spaces.
Can Talking Paintings AI run without internet?
Yes. With an On-Premise setup, the language model and voice run on the installation computer, so the character works without an internet connection. Hybrid and online setups are also available.
Where would you like to start?
Keep exploringReady to see Talking Paintings in action?
Book a demo and have a conversation with one of our Digital Humans, or tell us about your space, your audience and your story.