It stopped working: which permissions should I check?

Open System Settings, then Privacy & Security, and make sure Writhere is enabled under Microphone, Accessibility and Input Monitoring (plus Screen Recording if you transcribe calls). Then relaunch the app: macOS applies some of these only to a fresh start. You can check them anytime from the Autorizzazioni section in the app dashboard.

What are the system requirements?

A Mac with macOS 13 or later. Apple Silicon (M1 or newer) is recommended: everything runs on-device, and the AI features are dramatically faster there. Intel Macs work too, with longer processing times for call transcription and summaries.

Why does it ask for the Microphone?

To hear your voice while you dictate. The audio is processed on your Mac and never leaves it.

Why does it ask for Accessibility?

To type the dictated text straight into your apps and to catch the shortcut in any app. Without it, Writhere would be stuck in its own window.

Why does it ask for Screen Recording?

Only to hear the other side of a call you want transcribed: macOS gates system audio behind this permission. It is optional, nothing is filmed, and no audio ever leaves your Mac.

€49 forever — what's the catch?

There isn't one. The AI runs on your device, so there's no ongoing cost on our side to pass on to you. One payment, yours to keep.

Is my voice really private?

Yes. Everything is processed locally. Your audio and text never leave your machine — there's no server to send them to.

What happens when I switch computers?

Your license covers every device you own. Install Writhere on the new one and you're set — no account, nothing to migrate from the cloud.

Yes — improvements land as free updates, so the app you own keeps getting better at no extra cost.

July 23, 2026

Real-Time Speaker Recognition: Knowing Who's Talking While the Call Is Still Going

Most call transcription tools can tell you who said what, eventually, once the call has ended and a background pass has run over the full recording. Useful, but it means the answer to "who am I talking to?" only exists after the conversation is already over.

Quick answer

Matching a voice against previously saved voice samples doesn't have to wait for the call to end. Doing that match on each freshly recorded segment, as the call is still happening, means recognized voices show up by name in the live transcript and in a live chat about the call, while it's still in progress.

Why this is normally a post-call-only feature

Full, accurate speaker separation over an entire recording is usually run once, on the complete audio file, because it's more reliable with the whole conversation available at once. That's a reasonable tradeoff for accuracy, but it pushes every use of speaker names to after the fact.

What changes when recognition runs live

— Each short segment gets checked against saved voice samples as soon as it's recorded, not at the end.
— Only confident, named matches are shown live; anything uncertain stays generic rather than guessing and getting it wrong.
— A full, final pass still runs after the call for the definitive, fully labeled transcript, live recognition is a head start, not a replacement.

Where this actually helps

Asking "who's talking right now?" mid-call, or having a live transcript already show real names instead of "Speaker 1," turns a call tool from something you consult afterward into something useful during the conversation itself.

The bottom line

Knowing who's on a call shouldn't be something you find out after it's over. If the recognition can run live, there's no good reason to make people wait for it.