Frequently asked questions

The student logs in with an assigned ID and starts with a device check: listening to a test sentence, checking the microphone and confirming the recording notice. Then the student draws a topic from face-down cards, prepares and answers out loud. The answer starts with a self-directed exposition, followed by targeted follow-up questions. Closing the exam requires a separate confirmation.

The virtual examiner asks the questions. It appears on screen as a restrained, continuously looping video; the student hears each question in the headphones and reads the same text on screen. A supervisor is present in the room, and the final grade is decided by the teacher.

In notes mode students can type their own outline during preparation and see the recognised text while speaking. In speaking-only mode there is no note field: students move on with a few large buttons, a mouse and a microphone, and the transcript is shown after the exam is closed. In both modes the live answer is spoken.

No. The examiner focuses on content: it does not assess accent, speaking pace or confidence, does not hint at answers, and does not re-ask knowledge that was already properly demonstrated.

The question can be replayed, the student can signal that the answer is finished or that they do not know, and can ask the supervisor in the room for help – the request appears immediately in the supervisor’s overview. If a technical error occurs, the exam pauses and previously submitted answers are kept.

Currently in Hungarian: the exam interface, the examiner voice and speech recognition are Hungarian. The website is available in Hungarian and English.

Yes. After the exam is closed they can review the per-requirement analysis, the full question-and-answer transcript and the exam event log, and download the PDF report. The analysis shows weighted content coverage, not a grade; the final grade is decided by the teacher.

The institution’s teachers. Each topic can have a task, source material, an expected answer and detailed assessment criteria. The system can draft a proposal from the source material, but never approves anything automatically: only teacher-checked topics are used in live exams.

Requirements can be split into essential, expected and supplementary knowledge, weighted 3×, 2× and 1×. A demonstrated item earns a full point, a partially demonstrated one half a point. The summary is weighted content coverage, not an automatically assigned grade.

Based on what was said: it checks which essential content the student has already demonstrated, where clarification is needed and which requirements have not come up yet. Questions move towards the heavier requirements not yet demonstrated, with at most two questions per requirement.

Yes, but this does not affect exams already in progress: each exam session works from the curriculum captured at login, so the yardstick of an answer never changes afterwards.

The full roster – including students who have not logged in yet – in card and list views: who is checking devices, who has drawn a topic, who is preparing, who is answering and who has finished, plus the drawn topic, remaining time, connection status and help requests. Clicking a student shows the questions and answers in chronological order.

One laptop per student with a supported Chrome or Edge browser, a headset with microphone and a stable network connection. The system runs in the browser and needs no installation. Before institutional roll-out we recommend a room test with 30–40 real headsets.

The curriculum and exam sessions in a PostgreSQL database, audio recordings separately in persistent server-side storage. The storage location, access rights and retention period are set out in the agreement with the institution.

A large language model (currently the DeepSeek API) interprets answers and drafts topic proposals, and ElevenLabs speech synthesis provides the examiner’s voice. The student’s speech is converted to text by the built-in speech recognition of Chrome or Edge, which uses the browser vendor’s cloud service (Google for Chrome, Microsoft for Edge). These points are part of the institution’s data protection alignment.

Not at the moment. Students log in with an exam ID assigned by the teacher, staff with a username and password. Institutional integration can be discussed as part of the roll-out.

Pilot terms are agreed individually with each institution. Request a demo and we will get in touch.

Yes. A transcript and an audio recording are made of the answer; students are informed by the recording notice handed out on site and confirm it during the device check. The audio recording is stored on the server, separately from the transcript.

The public website uses no marketing or tracking cookies. Visitor analytics – when enabled – works without cookies and produces aggregate statistics only. Areas that require login use only the session cookie they need. Details: cookie notice.