New · AI Voice

Your translated words, in a voice that sounds like you

On a VivaLingua call, everyone hears the others in their own language, spoken aloud. With AI Voice, what they hear from you is no longer a standard voice. It is an AI voice made from a short recording of you, so your partner hears your words in Spanish, your in-laws hear them in Thai, and it still sounds like you.

Optional. Included at no extra cost, in all 41 languages, on iPhone and Android.

You say I miss you. How was your day? They hear, in a voice that sounds like you AI Voice Te extraño. ¿Cómo estuvo tu día?

How it works

1. Record once

In the app, speak for 30 to 60 seconds. During the recording the app shows you four words to read aloud. That confirms it is you, recording live, and not a playback of someone else.

2. Talk as usual

Start or join a call or an in-person session. Whenever you speak, your words are translated into each listener’s language and spoken in your AI voice.

3. Everyone knows it is AI

While your AI voice is speaking, listeners see an “AI Voice” label, in the app and on the guest page. It is a synthetic voice saying words you did not record, and nobody is left to guess that.

Where it works

Video calls, voice calls and face-to-face conversations, including groups, in sessions you host and in ones you join. All 41 languages, in any pairing: you speak your language and are heard in theirs.

A guest who joins from a link in a browser cannot create an AI voice, but hears yours. Anyone who joins with the app can use their own.

What it costs

Nothing extra. AI Voice is included. A call with it uses minutes exactly as a call without it does, and as always only the host spends minutes; everyone they invite joins free.

Privacy and control

VivaLingua does not keep your recording. It passes through our servers to Deepgram, which checks the four words, and to ElevenLabs, which makes your AI voice from it. Your name and email address are not sent with it.

It is not used to train anyone’s AI. We have switched off ElevenLabs’ model-improvement setting for our account, so your recording and your voice model are not used to train or improve its AI.

Only your own voice. Creating an AI voice from anyone else’s voice is against our terms, and so is using one to mislead people about who is speaking.

Delete it whenever you like. In Profile, any time. It is also deleted automatically if you do not use it for 12 months, or do not use VivaLingua at all for 6 months, and when you delete your account. The privacy policy has the full detail, in section 4.

Where it is available

In most countries. AI Voice is not offered in China, Malaysia or South Korea, in countries and regions under comprehensive US sanctions, or in the US states of Illinois, Texas, Washington and Colorado, which have their own laws on voice data. There, your translations are spoken in a standard voice and everything else works the same.

How it compares

Google Meet’s spoken translation also keeps something of the speaker: their intonation. It covers English paired with Spanish, French, German, Portuguese or Italian, on a paid Google plan. FaceTime translates into captions rather than speech. VivaLingua’s AI Voice works across all 41 languages, in any pairing, on calls and face to face, for the price of the minutes you already buy. There is a fuller side-by-side comparison of the built-in options.

Checked 12 September 2026. The Meet and FaceTime details come from Apple’s and Google’s own documentation and are changing quickly. The rest of this page describes VivaLingua; the terms and privacy policy are the full statement. The FAQ answers the common questions about AI Voice.

Try AI Voice on your next call

Pay as you go. Guests always join free.

Download on theApp Store Get it onGoogle Play