Voice + Context + Action · shipping now

They hear what you said.
Cue sees what you're doing.

Voice is how you tell Cue. Screen context is how Cue understands. AI action is what gets delivered. One hotkey, the full loop. Mac & Windows.

Try Cue free See how it works

Free forever for dictation · Mac & Windows

Voice
Captures intent
Context
Reads your screen
Action
Delivers the result

The thesis

Voice alone just gives you words on screen, that's what SuperWhisper, Wispr Flow, and Aqua Voice do. But the real question is never "what did you say," it's "what do you want done, given where you are right now." Cue captures all three: your voice (intent), your screen (context), and delivers the action. Each layer compounds the one below it.

The input you already know how to use.

Press a hotkey, speak. Cue transcribes, translates, and detects your language on the fly. Sub-3-second latency, 20+ languages, no training required.

01 · Dictation

Real-time speech-to-text

Sub-3-second latency for short utterances. Accuracy on par with or better than SuperWhisper, Wispr Flow, and Aqua Voice, powered by Deepgram Nova-2.

02 · Translation

Real-time voice translation

Speak Mandarin, write English. Speak Japanese, write Korean. Cue auto-detects your spoken language and writes in whichever one you need.

03 · Multilingual

20+ languages

English, Mandarin (Simplified + Traditional), Cantonese, Japanese, Korean, Spanish, French, German, Portuguese, Russian, Arabic, Hindi, and 8 more.

This is where Cue stops being a dictation app.

Cue reads your screen, knows which app is active, and understands the input field you're in. Same voice command means different things in Mail vs. Slack vs. a search box. Cue figures it out so you don't have to.

04 · Vision

Screen understanding

Cue captures a screenshot on agent invocation. Tasks adapt to what's in front of you without any explicit context dump. Reads text, UI, data, code, everything.

05 · App awareness

Input field detection

Cue knows if you're in a chat, an email, a search box, or a code editor. Formal tone in Mail, casual in WhatsApp, keyword mode in Spotlight. Zero mode switching.

06 · Selection

Selected text capture

Highlight a paragraph, press the hotkey, say "make this shorter." Cue reads what you selected and acts on it. No copy-paste gymnastics.

Say it. It gets done.

Voice + context turn into finished work. Fast path for text tasks (translate, polish, summarize) in 1-3 seconds. Full agent path for multi-step tasks with tools. Claude Sonnet and Opus under the hood.

07 · Polish

Context-aware refinement

Every dictation goes through a polish step that respects where you are. Full punctuation in email, short replies in chat, bare keywords in search. Never once-size-fits-all.

08 · Agent

Multi-step AI agent

"Scan my receipts and build an expense report." Cue plans, reads files, writes code, opens apps, and produces the finished artifact in under 60 seconds.

09 · Universal

Works in any app

No integrations, no plugins, no special adapters. If your app has a text field or a window, Cue works with it. Terminal to Slack to Figma.

Native desktop, local history.

Cue is a real desktop app, not a browser tab. Voice never leaves your hotkey, screenshots stay on-device until you trigger an agent task, history is 100% local. No account required for dictation.

10 · macOS + Windows

Cross-platform

macOS 13+ on Apple Silicon and Intel, plus Windows 10 1809+ / Windows 11 x64. Same hotkey, same voice, same features.

11 · Local-first

Local history & privacy

Every interaction stored in a JSONL file on your device. Nothing is uploaded without your trigger. Searchable offline forever.

12 · Instant

Hotkey activation

Fn on Mac, Alt on Windows. Long-press for push-to-talk, tap to toggle. Option key for pure dictation. No click, no menu, no delay.

What's shipping next.

We're heads-down on voice wake, long-form capture, and a Memory system that aggregates your history across every AI tool you use.

Voice Wake

"Hey Cue"

Hands-free activation without pressing a hotkey. Wake word customizable, runs fully local on your device.

Long-Form Voice

Meetings & videos

Auto-detect meetings, videos, and long-form speech. Cue transcribes, summarizes, and saves to your Memory without a hotkey.

Memory Aggregator

All your AI history, one place

Import ChatGPT, Claude, and local agent history. Cue becomes the single home for your relationship with every AI tool.

Follow Updates for weekly ship notes, or join our Beta Community.

All of this.
Free to start.

Unlimited voice dictation on day one. AI agent on day two. No credit card required.

Download Cue

Free forever for dictation · Mac & Windows