Live voice translation in Zoom: just talk, we'll handle the rest

Real-time audio translation for Zoom Meetings makes multilingual collaboration as simple as clicking a button.

Global teams are the norm. But when half the room speaks Mandarin, and the other half speaks Spanish, meetings get complicated fast. Translated captions help, but reading subtitles while trying to stay engaged in a live conversation? That's multitasking nobody signed up for.

Voice Translator for Zoom Meetings takes a different approach. Instead of asking participants to read along, it delivers spoken translations directly into their ears — in real time. You speak your language. They hear theirs. Everyone can participate in the conversation.

How it works

Voice Translator uses AI to process meeting audio through three steps: automatic speech recognition, machine translation, and text-to-speech — all happening in near real time. The result is a translated audio stream that plays alongside (or in place of) the original speaker's voice.

From inside a Zoom Meeting, you turn it on with a single click from the meeting toolbar, pick your speaking language and the language you want to hear, and you're live. There's no complex setup, no pre-meeting configuration, and no need to coordinate with other participants. Each person controls their own translation settings independently.

Five languages at launch, more on the way

Voice translation currently supports English, Chinese, Spanish, French, and Japanese. Additional languages, including Portuguese, Arabic, German, and Italian, are planned for later in 2026.

We're also working on capabilities that will make the experience even more natural and flexible:

• Voice cloning — translated audio that preserves the original speaker's voice characteristics, so it sounds like them speaking in your language.
• Translation projection — the ability to speak in your language and have everyone else hear you in theirs. If you speak English, participants can hear you in Spanish, French, or any other supported language — automatically.

Built for focus, not distraction

The core design principle here is simple: keep people in the conversation. Translated captions require you to split your attention between reading and listening. Voice translation lets you do what you'd do in any meeting — listen, react, and respond naturally.

You can fine-tune the experience with a volume balance slider that controls how much of the original speaker's voice you hear versus the translated audio. And you can choose between voice styles for the translated output, so it sounds natural to you.

A small voice translator icon appears next to the active speaker's name to let you know translation is working — visible only to you, not the rest of the meeting.

When this matters most

Live voice translation is useful anywhere language differences slow things down:

• Global standups and team syncs — distributed teams where not everyone shares a common language can run meetings without defaulting to one dominant language.
• Cross-regional all-hands — leadership can address the full organization in their native language while every employee hears the message in theirs.
• Client and partner calls — external meetings with international stakeholders become smoother when nobody has to struggle through a second language.
• Onboarding across borders — new hires in different regions can participate fully in training sessions from day one.
• Multilingual brainstorms — when people can think and speak in their strongest language, the ideas get better.

Privacy and data handling

Voice translation processes audio in real time to deliver the feature. No meeting audio is stored, no voice prints are created, and no persistent user profiles are built from translation data. The feature processes what it needs for the meeting and discards it.

Availability

Voice Translator is available for Pro, Business, and Enterprise accounts through the Zoom desktop app (Windows and macOS, version 7.0.0 or higher). It's included with ZoomMate or available as a standalone Live Translation Add-on.

The most advanced ZoomMate capabilities — agentic search, deep research, workflow automation, and AI-generated deliverables — are available as metered services that use AI credits. Voice Translator uses this same credit-based model, so usage scales with your needs.

Note: Voice translation may not be available in all regions or for all industry verticals.