In-Person Mode enables two or more people to have a multilingual conversation face-to-face using a shared device. Each participant speaks in their own language, and the system transcribes, translates, and optionally speaks the other party’s words in real time. This mode is ideal for customer service counters, help desks, outreach booths, or frontline community interactions.

The device (typically a tablet or phone) acts as a live interpreter. Users take turns speaking, and each utterance is instantly transcribed on-screen and translated into the target language(s). Voice playback can also be enabled to provide a natural listening experience, especially useful in low-literacy settings or with elderly participants.

Because the conversation happens in a shared physical space, the interface is designed to be easily viewable and accessible from both sides of the device. Turn-taking cues and visual separation of each speaker’s contributions help prevent confusion. The system supports offline fallback and low-bandwidth operation, making it reliable even in remote or pop-up environments.

This mode is especially powerful for cross-language engagement in public services, healthcare triage, visitor services, or community safety settings—where fast, human-to-human communication is needed but interpreters are unavailable.