Video Call Mode enables participants to join the same call while speaking and hearing different languages. Each person simply speaks in their native tongue, and the platform handles real-time transcription, translation, and neural voice playback for all other participants. This makes it possible to hold multilingual meetings without an interpreter.

As someone speaks, their words are transcribed live and translated into each participant’s preferred language. Text appears as captions, while translated audio is delivered in a natural-sounding voice. Participants hear and read the conversation in a language they understand, even if no one else on the call shares that language.

Video Call Mode is especially useful for remote consultations, multilingual staff briefings, global customer support, or community engagement sessions with interpreters in short supply. It supports one-on-one or group conversations and allows everyone to fully participate in real time.

The interface is designed to minimize delays and keep conversations flowing naturally. Users can view side-by-side transcripts, replay key phrases, or download a full meeting summary afterward — all in their preferred language.