Give your agent
eyes and ears.
Record your screen, dictate what you want, and Zerro turns it into exactly what you need — an agent prompt, a message, a snippet, a written-up document, or simply a clear answer to your question.
v1.0 · Apple Silicon · Signed & notarized
What is Zerro?
Show your screen. Say what you want.
Zerro is a native macOS menu-bar app that turns a screen recording and a few spoken words into exactly what you need — an agent prompt, a message, a code snippet, or a written-up document, ready to paste into any AI tool or send to a person. Or, when you just want to understand something, a clear answer in plain language.
Everything runs locally first, and you bring your own keys — no servers in the middle, no account required. Talking is faster than typing, and Zerro turns what you say into something you can paste, send, or run.
Works with
Use it for
- Hand a coding agent real context
- Draft a message about what's on screen
- Grab the exact formula or snippet you need
- Turn messy notes into a clean write-up
- Get a confusing screen, error, or chart explained
How it works
Record. Speak. Copy.
Think voice dictation — but instead of plain text, you get exactly what you need: a ready-to-use artifact, or a straight answer. No new app to learn; the whole flow runs from the menu bar.
Select a region
Hit the hotkey, drag to frame the part of your screen you want Zerro to see. Native macOS crosshair, no window switching.
Dictate what you want
Talk it through like you'd explain it to a teammate. Point at things, change your mind, ramble. Zerro records up to 3 minutes.
Zerro processes locally
Audio gets isolated and frames get downsampled on your machine. Then a single API call turns it into the right result — a ready-to-use artifact, or a straight answer.
Paste it anywhere
It lands on your clipboard — agent prompt, message, snippet, or document — ready to drop into Cursor, your inbox, a sheet, or wherever it's headed.
The output
The prompt writes itself.
Every recording becomes exactly what you need — an agent prompt, a message, a snippet, or a document, written up and ready to use. Or, when you just want to understand something, a clear answer in plain language.
One recording. The right artifact.
Instructs your AI agent to fix the silent failure on the checkout promo-code field and surface a clear validation error.
Fix the promo-code validation on the checkout Order Summary.
- 1. Locate the "Apply" button beside the promo-code field (current value: SAVE20) in the Order Summary panel.
- 2. When an applied code is invalid or expired, the field currently does nothing — no error, no spinner, no state change.
- 3. On an invalid code, render an inline error directly beneath the field in red (e.g. "This code is expired or invalid").
- 4. Keep the existing layout and totals; this is a validation fix, not a redesign.
Example output. Every prompt is generated from your real recording.
Built right
Native, local-first, no surprises.
Zerro is built the way you'd build it if it were your tool.
Native Swift & SwiftUI
A real menu-bar app, built on ScreenCaptureKit. Not an Electron tab pretending to be a Mac app.
Local-first processing
Audio isolation and frame downsampling happen on your machine before anything leaves it.
Bring your own key
On BYOK, your OpenAI, Gemini & Anthropic keys are stored in macOS Keychain and recordings never leave your Mac.
Cost-bounded by design
A 3-minute hard cap on every recording keeps each request fast, cheap, and predictable.
Signed & notarized
Distributed direct as a code-signed .dmg. macOS Gatekeeper will not complain.
Sparkle auto-updates
Updates ship through Sparkle, the standard for indie Mac apps. You stay current without thinking about it.
How it compares
A different category.
Dictation tools give you text. Screen recorders give you a video. Zerro gives you the finished result — a prompt, message, snippet, or document, or a straight answer to your question.
| Feature | Zerro | Wispr Flow | Loom |
|---|---|---|---|
| Primary input | Screen + voice | Voice | Screen + voice |
| Output | Ready-to-use output | Dictated text | Video link |
| Formats output for the taskPrompt, message, snippet, or doc. | — | — | |
| Local-first processing | — | — | |
| Bring your own API keys | — | — | |
| Native macOS app | — | ||
| Pricing modelPay once, own it forever. | One-time ($69) | Subscription | Subscription |
Comparison reflects Zerro's positioning. Competitor capabilities change over time — check each product for current details.
The shift
Now we're talking.
The keyboard was never the point — it was just the only interface we had. As agents get better at acting on what you actually mean, typing out every instruction by hand starts to feel like the bottleneck it always was.
You think faster than you type. You talk faster than you think. Voice closes that gap — and dictation is becoming the default. Zerro is built for that future: less typing, more talking.
Words per minute
You speak nearly 4× faster than you type. The keyboard has been the bottleneck all along.
Pricing
Let us handle the AI — or bring your own keys.
Try it free, then choose the path that fits — we handle the AI, or you bring your own key.
Managed
Most popularWe handle the AI — no keys, no setup.
- 40 free credits to start
- 300 credits per month≈ 75 generations with Gemini 3.5 Flash, or ~30 with Claude Opus.
- 6 models to choose from — Claude, GPT & Gemini
- Top up anytime — Boost (200 credits, $10) or Power (500 credits, $22)
- We manage all token usage — no API keys
- Cancel anytime
BYOK
Bring your own keys. Runs fully on your Mac.
- 40 free credits to start
- Includes 1 year of updates — your installed version keeps working after
- Bring your own OpenAI, Gemini & Anthropic API keys
- All 6 models — Claude, GPT & Gemini
- Keys stored in your macOS Keychain
- Recordings never leave your Mac
- No subscription, no account
Managed sends your recording to Zerro's server to generate the result. Bring-your-own-key stays fully on your Mac — recordings never leave your machine.
Prices listed in USD. The one-time BYOK purchase includes 1 year of updates; your installed version keeps working after that.
FAQ
Questions, answered.
Record it. Paste it.
Zerro in between.
Stop describing what you want. Show it. Zerro turns the recording into exactly what you need — a prompt, a message, a snippet, a document, or a straight answer.
v1.0 · Apple Silicon · Signed & notarized