Live Captions for Microsoft Teams and Zoom Without a Bot Joining Your Call

You know the moment. You're two minutes into a call and a little notification slides across everyone's screen: "Otter Notetaker has joined the meeting." Someone asks whose bot it is. Someone else quietly wonders what happens to the recording afterwards. It's a small thing, but it changes the tone of the call, and more than a few people simply say no to the whole idea because of it.

We think there's a better way to get live captions, one that doesn't involve a stranger's software sitting in on your conversation. PeekoType now provides real-time captions for Teams, Zoom, Google Meet and any other video call, and it does it without anything joining the meeting at all.

The short version: PeekoType listens to your own PC's audio directly, so it can caption any call in real time without a bot appearing on the participant list and without your audio ever leaving your device. It works in 49 languages and is included in PeekoType at £39 once, with a free 14-day trial.

How captioning without a bot actually works

Every meeting bot you've ever seen join a call works the same basic way: it dials in as a participant, listens to the meeting like anyone else on the call, and sends what it hears off to a server somewhere to be processed. That's why it shows up on the attendee list, and it's why the meeting's audio ends up on someone else's infrastructure.

PeekoType takes a completely different approach. Rather than joining the call as a participant, it listens to the audio your own computer is already playing, the same sound coming through your speakers or headset. Nothing dials in, nothing appears on the participant list, and nobody else on the call ever knows PeekoType is running. The captions appear on your screen, generated entirely by your own PC, in real time.

Works with the tools you already use

Because PeekoType captions whatever audio your Windows PC is playing, it isn't tied to one piece of call software. It works equally well with:

There's nothing to configure per platform and no separate plug-in to install for each one. If it makes a sound through your speakers, PeekoType can caption it.

Forty-nine languages, entirely on-device

Live captions run on exactly the same on-device speech engine that powers PeekoType's dictation and translation features, and support 49 languages. That makes it genuinely useful for international teams, language learners, and anyone who joins calls where English isn't the first language of every participant. Because the whole process runs locally, there's no round trip to a cloud translation service adding delay, and no dependency on an internet connection staying fast and stable throughout the call.

If your team regularly works across languages, our guide to voice typing for international teams covers the wider picture of how on-device dictation and captioning fit into multilingual work.

Why "nothing leaves your PC" is the whole point

Meeting audio is some of the most sensitive material most of us produce day to day. It contains other people's voices, opinions and sometimes deeply confidential information, none of which those people necessarily agreed to have processed by a third party. Cloud-based captioning and meeting bots require exactly that: your call's audio is sent off to be transcribed somewhere you don't control.

PeekoType's approach avoids that question entirely, because there's nothing to send. Captions are generated on your own machine and stay there. This is the same principle behind everything else we build, covered in more detail in our guide to GDPR-compliant voice typing, and it's exactly why legal and clinical professionals tend to be the first to ask whether a tool sends audio to the cloud before they'll touch it.

A quieter kind of accessibility win too

Live captions aren't only about privacy. For anyone who finds it easier to follow a conversation with text alongside the audio, whether that's because of a hearing difference, a noisy environment, or the way their brain processes spoken information, on-screen captions make a real difference to how much of a meeting actually lands. Our piece on voice typing for dyslexia, ADHD and neurodiverse minds explores this from the writing side, and the same logic applies just as strongly to reading along with a live conversation.

Who this is for

Who you are Why bot-free captions help
Client-facing professionals Follow every detail of a call without an unfamiliar bot appearing on a client's meeting
International and remote teams Read along in real time across 49 languages without a translation delay
Anyone hard of hearing or working in a noisy space On-screen text for every call, without needing to ask a platform to enable it
Privacy-conscious teams No meeting audio ever leaves the building, let alone the country

Getting started

  1. Download PeekoType and start your free 14-day trial. No card required.
  2. Join your next Teams or Zoom call as normal.
  3. Turn on live captions in PeekoType and watch them appear in real time, entirely locally.

If you'd also like a proper written record after the call rather than just live text on screen, pair this with our new offline file transcription with speaker detection, available in PeekoType, which turns a recorded meeting into a full transcript with each speaker labelled.

The bottom line

Live captions shouldn't require inviting a stranger's software into your meeting. PeekoType gives you real-time captions for Teams, Zoom and any other video call, in 49 languages, without a bot ever joining and without your audio ever leaving your PC. It's included in PeekoType at no extra cost.

Start the free 14-day trial from our homepage, or get in touch at support@peekotype.com if you have any questions before you do.

Caption your next call, privately

PeekoType's live captions work with Teams, Zoom and any video call, in 49 languages, with no bot and nothing sent to the cloud. £39 once, free for 14 days, no card required.

Start Free Trial