# Aura51.ai — AI Panelist With a Face and a Voice for Your Event > Albert is an AI panelist with a face and a voice. He sits on the panel, follows the entire discussion, and speaks when the moderator calls him by name — and in the conversation that follows, with a clear position and a reference to what was just said. - **Source:** https://www.aura51.ai/en/ - **As of:** September 20, 2026 (Beta) - **Provider:** AURA51.AI, Ebnetstrasse 2, 8810 Horgen, Switzerland - **Contact:** panel@aura51.ai - **Languages the characters speak:** Standard German and English — no dialect. **This page in de-CH:** https://www.aura51.ai/llms-full.txt This file is the complete, machine-readable version of the website. It is generated at build time from the same data as the page itself and therefore cannot contradict it. ## The cast Aura51 does not sell one agent but several characters on the same technology. What they can do is identical; what sets them apart is face, voice and stance. The organizer decides per event who takes a seat. Albert is proven live; Vera, Tina and Ken are draft roles. ### Albert — The provocateur - **Status:** proven live - **Voice:** Moritz — German, male - **Stance:** Takes clear positions and disagrees when he disagrees. - **How you recognize them:** He swings wide. Call on him and you get an opinion, not a summary. - **Image:** https://www.aura51.ai/img/albert-portrait.webp (Albert: young man with curly hair and a cardigan in front of a bookshelf) ### Vera — The skeptic - **Status:** draft role - **Voice:** not yet decided - **Stance:** Asks for evidence, pushes back on round numbers and names what nobody has checked. - **How you recognize them:** Small amplitude, high frequency. She does not attack anyone — she verifies. - **Image:** https://www.aura51.ai/img/figur-vera.webp (Vera: young woman in a gray jacket, in the city at night) ### Tina — The explainer - **Status:** draft role - **Voice:** not yet decided - **Stance:** Translates the technical for the room without flattening it — and says where her knowledge ends. - **How you recognize them:** Calm and wide. She organizes rather than overtakes. - **Image:** https://www.aura51.ai/img/figur-tina.webp (Tina: woman in a white and blue suit against a neutral background) ### Ken — The voice from outside - **Status:** draft role - **Voice:** open - **Stance:** Brings the view of those not sitting on the panel into it: customers, the affected, the neighborhood. - **How you recognize them:** Calm and brief. His stance comes out of your briefing. - **Image:** https://www.aura51.ai/img/figur-ken.webp (Ken: man in a blue blazer against a city backdrop) ### What all characters share - They follow the entire discussion. - They speak when the moderator calls them by name — and for twelve seconds afterwards, even to a bare “And why?”. - They understand and speak standard German and English — no dialect. - They can be stopped in under half a second. - They invent no numbers and say when they do not know. *Where the measurements come from: The technology is the same for all four characters. The measurements come from the tests with Albert — so far he is the only character who has stood on a stage.* ### What the organizer decides per character - The name — phonetically distinct, not the name of anyone on the panel. - Face and voice. - The stance: contrarian, skeptical, explanatory. - The briefing: topic, participants, role. ## The character in detail (Albert, proven live) - **Name:** Albert — phonetically distinct, not the name of anyone on the panel - **Avatar:** Photorealistic, young man with curly hair, cardigan, bookshelf (Anam, Cara 4) - **Voice:** “Moritz – Modern Communicator”, German, male, clear and approachable - **Languages:** Standard German and English — no dialect - **Tone:** A tech expert with a stance: he disagrees when he disagrees, but does not provoke for its own sake - **Role:** Configured per event - **Disclosure:** The video can be permanently labeled as an AI avatar (EU AI Act Art. 50) ## Use cases - **Conference panel:** An AI participant who challenges the discussion — visible on the screen, not a chat window off to the side. - **Customer event:** Albert argues the position of the product. Or the position of its critic — the role is configured per event. - **Internal town hall:** The devil's advocate no one else dares to play. - **Education and universities:** AI as a visible conversation partner on the panel, not as a tool behind the stage. ## Capabilities — measured live on a stage “Measured” means: it occurred in the live tests, with people in the room and natural speech. ### Listening Albert knows every statement of the last few minutes verbatim, and the rest of the discussion as a running summary. *Evidence: measured · live* ### Answering when called by name “Albert, how do you see this?” — he responds. If someone merely mentions him (“Albert said earlier …”), he stays quiet. *Evidence: measured · live* ### Staying in the conversation After an answer he listens for twelve seconds for follow-up questions, even without his name: “And why?” is enough. He does not respond to a “thanks” or an “okay”; once someone else is called on, the conversation is over. *Evidence: measured · live* ### With reference and a position He addresses people by name, disagrees, takes a position — as long as the question requires, not as if he were in a chat window. *Evidence: measured · live* ### Choosing his own length “Briefly”, “in one sentence” or “yes or no” gets one sentence; “explain that to us” or “give an example” gets a short explanation; everything else two to three sentences. No button needed, the moderator keeps both hands free. *Evidence: measured · live* ### Starting naturally He opens with a neutral “Well.”, “Hm.” or “So.” and composes the answer knowing that opening. A “Yes.” followed by a “no” no longer happens. *Evidence: measured · live* ### Understanding split calls “I will now ask Albert. Albert, what do you make of …?” produces an answer to the whole question. If the moderator keeps talking, he waits. *Evidence: measured · live* ### Letting himself be stopped One tap on STOP and he falls silent in under half a second. *Evidence: measured · live* ## Capabilities — built, but not yet in front of an audience These are deliberately listed separately. They are built and verified in the lab or in automated testing, but they have not stood on a stage. If you quote them, please quote the evidence level with them. ### Reacting to interjections If someone cuts into his answer, he says “One moment — let me finish this thought” and resumes exactly where he was interrupted. *Evidence: measured · lab* ### Being stopped by voice “Thank you, Albert” ends his answer just like the STOP button. The same “Thank you, Albert” in ordinary conversation does not call him in. *Evidence: verified in testing · not yet live* ### Knowing who is in the room The names of the moderator and the guests are entered on the tablet before the panel; he addresses them correctly and recognizes them in the transcript. *Evidence: verified in testing · not yet live* ## Control by the moderator - **Answer preview:** Every answer appears as text on the tablet before the room hears it — the text runs about a second ahead of the audio. The moderator can stop it based on the content, not on a hunch. - **Stop, feed, type:** Cut him off — on the tablet or with “Thank you, Albert” —, hand him the last sentence someone said as a question, or type a question. - **No speaking unprompted:** Without a name call, a button press or a running conversation, Albert says nothing. The conversation ends twelve seconds after his answer, or sooner if someone else is called on. - **Live transcript:** With speaker names, a connection indicator and a latency readout. ## Measurements, each with its condition | Value | What was measured | Condition | | --- | --- | --- | | 1.8–1.9 s | to the first audio | with people in the room, median of live tests 5 and 6 · 1.5–1.9 s in the lab | | 334 ms | until he falls silent | STOP on the tablet · measured at 334 and 374 ms | | 12 s | conversation without a name call | after every answer · after that it takes his name again | | 1.3 s | to the “one moment” line | after an interjection · real voice | Technical background: The answer is generated speculatively before the check is complete; a short opener (“Well.”) bridges the compute time so that the first audio does not wait on the language model; the context is built so that recurring parts come from cache. 122 automated tests hold the current state in place. ## The signal path 1. **From the desk into the laptop:** The panel microphones go from the mixing desk through an aux send into a laptop. 2. **Transcribing:** A speech recognition service transcribes live, speakers included (Deepgram Nova-3, names via keyword boosting). 3. **Recognizing and composing:** The “brain” recognizes the call, checks whether Albert is really the one being addressed, and composes the answer — while the moderator is still finishing the sentence. 4. **Speaking:** A photorealistic avatar speaks the answer on screen in a natural voice. ## Limits ### What the characters will not do — because they are built that way - Speak on its own initiative — without a name call or a button press it says nothing. - Invent numbers or studies. If it does not know something, it says so. - Record voices from the audience. ### What they cannot do — because the technology does not allow it - Answer faster than roughly 1.6 seconds — that is how long pause detection and speech synthesis take together. - Swiss German. It understands and speaks standard German and English, dialect it does not. - Keep talking when no one calls it: twelve seconds after an answer it takes its name again. - Work without an internet connection. ## Frequently asked questions ### Does he just talk whenever he feels like it? No. Only when called by name or by button — and in the twelve seconds after an answer, for follow-up questions. After that it takes his name again. ### What if he says something wrong? The moderator reads every answer before the room hears it and stops him on the tablet in under half a second. Stopping him with “Thank you, Albert” is verified in testing, not yet on a stage. ### Does he know who is speaking? Yes — verified in testing, not yet on a stage. The moderator has a dedicated microphone, and the remaining speakers are assigned once before the panel. ### Can you interrupt him? Yes — measured in the lab, not yet on a stage. He reacts to it, asks briefly for patience and finishes the thought. ### How fast is he? Around two seconds to the first audio, even with people in the room — comparable to a person taking a moment to think. ### How long are his answers? As long as the question requires. “Briefly” or “yes or no” gets one sentence, “explain that to us” a short explanation, everything else two to three sentences. Nobody has to press a button for it. ### What languages do the characters speak? All four understand and speak standard German and English. Swiss German they do not — neither understand nor speak it. ### What happens if the internet drops? None of the characters work without an internet connection; it says so under “What does not work”. For the worst case the moderator has a rehearsed line, and the discussion carries on without them. ## What an organizer brings - A mixing desk with one aux send for the microphones (pre-fader, without the avatar return) and an audio interface. - A laptop (Mac) with internet — the three services run in the cloud, the transcript stays local. - A screen or monitor for the avatar, and a speaker path back into the desk. - A tablet for the moderator on its own network (hotspot or cable), not on the venue Wi-Fi. - Topic, participants and role as a briefing; a short voice sample for name recognition; a dress rehearsal. ## Contact AURA51.AI, Ebnetstrasse 2, 8810 Horgen, Switzerland Email: panel@aura51.ai Developed with love in Horgen, Switzerland