Listening is visible
Vozu does not imply background listening. The live state appears while the session is running and stops when you end it.
Speech in, translation out
A voice translator that shows its work.
Vozu listens only during an explicit session, shows speech as it develops, and translates the finalized turn. You can read the result or play it through an available system voice.
A microphone, internet connection, and compatible device voice are required. Noise, accents, network conditions, and provider availability can affect results.
Draft is not final
Provisional words can still change. Vozu distinguishes them from the finalized turn that is sent for translation.
Playback has limits
Spoken output uses an on-device system voice. Availability and voice quality vary by language and device.
What happens to the audio?
On mobile, audio streams from the app to Soniox using a temporary session key. Soniox processes speech so Vozu can receive transcript events. Finalized text is translated through Gemini. The Vozu backend does not store audio, transcript text, translations, or text-to-speech content, but these processors still receive the content needed to perform their part of the service.
Read the full data flow and retention boundaries.
What Vozu does not claim
Vozu is not an offline translator, simultaneous interpreter, call translator, meeting recorder, or guaranteed replacement for a human interpreter. The launch product is a turn-based mobile conversation tool.
See both sides of the exchange.
The conversation view keeps the source and translation together for the next person.