Real-time Vietnamese translation on your Mac

How to set it up

1. 1
   Open Tingdong and choose “Live Listen”

   Set the source to “Screen sound” so it captions the video or the call audio rather than the room. Vietnamese is detected, not selected.

2. 2
   Press Start

   Captions float over the player or the call window: Vietnamese on top, English below, updating before the sentence ends. You can have the English read aloud instead.

3. 3
   For a call, switch to “Call Translation”

   Choose Tingdong Microphone in the mic menu of FaceTime, Zoom, Telegram or Zalo for Mac, or hand an iPhone call to the Mac over Bluetooth. You speak English, they hear Vietnamese.

Tones, and a north–south split you will hear immediately

Vietnamese distinguishes words by tone, so the same syllable is several different words depending on pitch, and northern and southern speech differ enough in tone inventory and pronunciation that a system trained loosely on one can misread the other. On top of that, most of what an English speaker actually needs to understand — a voice message, a phone call, a wedding video — has no text version anywhere, so subtitle-based or browser-extension tools have nothing to attach to. Tingdong captions the audio itself and keeps context across sentences, which is what makes a long family call follow-able rather than a list of disconnected guesses. Language is detected per phrase among 60+ inputs, so relatives who switch between Vietnamese and English in the same sentence do not break the captions.

Frequently asked questions