Home/Docs/Video & Calls
📹 Powered by LiveKit

Video & Audio Calls

Real-time HD video, audio, and screen sharing powered by LiveKit. Call or hail a colleague, share an AI-watched screen, and read live captions with on-the-fly translation — all without leaving your organization.

🚪Join a roomCall or hail a colleague
🖥️Share your screenOr hail to ping people
🔤Live captionsWith on-the-fly translation
📝Saved transcriptSearchable AI context
A call from start to finish — join, share or hail, read captions, and keep a searchable transcript.

Room kinds

Your Office AI uses a few different kinds of real-time room, each for a different purpose.

RoomWhat it's forWho's in it
Organization presenceAmbient presence — see who's around. Auto-connects when an organization is active.Members of the organization
Solo-AI roomShare your screen and mic with the AI only; the AI can see a preview of your screen.Just you and the assistant
Workspace roomDirect calls and hails within a workspace.Workspace members you invite

Call vs. Hail

Within a workspace room, Call and Hail use the same underlying room but start interaction differently:

  • Call — you join the room directly, ready to talk.
  • Hail — you send an attention ping to selected people, like knocking on a colleague's door before stepping in.

You can multi-select participants in the grid and then batch Call or Hail them at once. Pin a participant to keep them front and center.

💡
Call vs. Hail

Use Hail when you're not sure someone is free — it's a gentle ping. Use Call when you've already agreed to talk and want to jump straight in.

Starting a call

  1. Open a workspace

    Go to the workspace whose members you want to talk to.

  2. Choose Call or Hail

    Select one or more participants in the grid, then Call to join directly or Hail to ping them first.

  3. Set up your devices

    Pick your camera and microphone, then join. You can turn your camera off to go audio-only.

  4. Share and caption as needed

    Share your screen, and toggle live captions — with translation — from the call controls.

AM
Alex M.👁 watching
JK
Jordan K.
YO
You
🖥Alex M. is sharing their screenLIVE
"…so if we look at the dashboard metrics for last week…"
🎤Mute
📷Cam
🖥Share
🔤Captions
🚪Leave
A workspace call — participant grid with a screen share and live captions enabled.

In-call controls

The call toolbar gives you control over your experience.

ControlWhat it does
🎤 Mute / UnmuteToggle your microphone.
📷 Camera On / OffStart or stop your video; turn it off to go audio-only.
🖥 Screen ShareShare your entire screen, a window, or a browser tab.
🔤 Live CaptionsTurn captions on; choose plain transcript or translated text.
📌 PinKeep a chosen participant front and center in the grid.
🚪 LeaveExit the call; others stay connected.

The "watching you" indicator

Your Office AI shows connection-quality stats for the call, alongside a "watching you" indicator that shows who is currently subscribed to your video.

Screen sharing

Share your content with one click. Your Office AI uses the browser's native screen-capture API and LiveKit's simulcast encoding to keep your share crisp even on slower connections.

  • Entire screen — share everything on your display.
  • Application window — limit sharing to a single app.
  • Browser tab — share just one tab.

In a solo-AI room, your shared screen is also previewed to the assistant, so you can ask it about exactly what you're looking at.

Live captions & translation

Turn on live captions to read what's being said in real time. The overlay has three states — off, transcript, and translation — so a multilingual team can follow along in another language on the fly. Captions are driven by the server transcription pipeline; see Transcription for how transcripts are produced, saved, and made available to the AI.

ℹ️
No in-app recording button

Your Office AI does not have a one-tap "record this call" button. "Recording" means the server-side transcription pipeline, which produces text — captions and saved transcripts — rather than a video file. What's saved, and who can access it, is controlled by the transcription access policy.

Cross-device beaming

If you're signed in on more than one device, you can beam things between them with remote commands — start a screen share, open a URL, or hand off an AI chat to another device. You can even drag a participant, skill, agent, knowledge folder, canvas, research report, workspace, or integration onto a device to send it there.

Voice-agent overlay

When you talk to the AI by voice, a full-screen overlay shows a waveform and live transcript and lets you barge in to interrupt. A persistent mini call module keeps the session handy as you move around the app.

⚠️
Camera & microphone permissions

If your camera or mic aren't working, check that your browser or OS has granted Your Office AI permission to use them. On macOS: System Settings → Privacy & Security → Camera / Microphone, then reload. For network issues, ensure your firewall isn't blocking the UDP ports LiveKit uses; it falls back to TCP/TURN for NAT traversal when a direct connection isn't possible.