Press a hotkey and speak. Cue can type in a focused field, transcribe meetings, use your screen as context, and help finish the task in the app you're using.
May 2026 Gemma 4 benchmark: 44% lower polish latency → Featured in Google DeepMind's Gemmaverse ↗
Messenger
WeChat
WhatsApp
Discord
Telegram
Gmail
Calendar
Zoom
Meet
Sheets
Drive
Slides
LINE
SignalMessengerWeChatWhatsAppDiscordTelegramGmailCalendarZoomMeetSheetsDriveSlidesLINESignal
Notion
Figma
Cursor
Google Docs
YouTube
Spotify
Steam
Chrome
Safari
Linear
Obsidian
Xcode
OBS
TerminalNotionFigmaCursorGoogle DocsYouTubeSpotifySteamChromeSafariLinearObsidianXcodeOBSTerminalNo menus, no commands to memorize.
Wherever you are, whatever you're doing. Cue is already there.
Don't worry about how. Cue already sees what's on your screen and figures out the rest.
Come back to a finished result. And next time? Cue already knows how you like it done.
New to Cue? Follow the voice typing guide, try a first Voice Agent task, or learn voice workflows with Claude Code and Codex.
Cue helps you prepare drafts and actions for review without leaving your current workflow.
Inbox
1 of 38
Start with the app and context already in front of you.
A few things people do with Cue every day.
Give Cue the photos and notes you choose; it can draft a travel-site structure for you to review before publishing.
Use visible source material to draft a research checklist and questions. Verify every figure; this is not financial advice.
Choose the receipt data to use, then draft an expense table for you to check against the originals and your company policy.
Select the photos and context, then draft captions and a portfolio structure for you to edit and publish yourself.
Provide the competitors and source material, then draft a briefing outline whose facts and citations you verify.
From the data you choose, draft chart and table ideas, then review the calculations and presentation.
Call just ended, brain already elsewhere? Dictate the rough recap and Cue turns it into action items.
Nobody wants to write documentation. So don't. Say "document this" and let Cue be the responsible one.
A hands-free agent that actually does things.
| Feature | Siri | ChatGPT | Cursor | Cue |
|---|---|---|---|---|
| Hands-free control | ✓ | ✗ | ✗ | ✓ |
| Understands your context | ✗ | ✗ | Code only | ✓ supported apps |
| Executes tasks on desktop | Limited | ✗ | Terminal only | ✓ |
| Works across supported apps | ✗ | ✗ | ✗ | ✓ |
| No typing required | ✓ | ✗ | ✗ | ✓ |
| Local copy; signed-in thread sync; request-time cloud processing | ✗ | ✗ | ✓ | ✓ |
| Free to start | ✓ | Limited | Limited | ✓ |
Cue is a desktop voice agent for Mac and Windows. Press a hotkey and speak to type, transcribe a meeting, use screen context, or help finish a task in a supported app.
Cue is a desktop voice agent that starts from your voice and current desktop context. It can transcribe, use your screen as context, and help finish a task in a supported app instead of stopping at a chat response.
Cue is free to start. Cue Plus is $19.99/month. Compare plans.
Read Cue's Privacy Policy for details about data and requests.
Cue is available for Mac and Windows. Current releases are 0.7.0 for macOS and 0.5.62 for Windows.
Built by
You talk to your computer all day. To Slack, to ChatGPT, to yourself. Why not just tell it what to do?
We got tired of clicking through the same 47 steps every day. So we built Cue — and let AI agents build most of it. One founder, six AI teammates, zero patience for busywork.
Free to start. Ready when you are.
