Write at the speed of thought, privately.

Your voice never leaves your Mac.

Why it exists

Free public beta · Apple Silicon · 8 GB RAM · macOS 13 Ventura or later


Watch it work.

Normal mode screen recording goes here · assets/video/normal-mode.mp4

Hold Fn, speak, release. Clean text lands where your cursor is.


Local-first. Private by architecture.

i.

Runs on your Mac

On-device Whisper, sized to your Mac's memory. Audio never touches the disk.

ii.

Works in any app

Text lands at your cursor. Notes, Notion, Slack, VS Code, Mail.

iii.

English, Indian, Tanglish, Hinglish

Vocabulary packs tuned for code-switched speech, not a generic toggle.

Four steps. Your voice never leaves your Mac.

Listen

Hold Fn and speak.

Transcribe

On-device Whisper.

Clean

Filler and punctuation.

Type

Text at your cursor.


Built to do one thing, and stay out of the way.

Three writing profiles

Raw, Clean, or Refine via a local Mistral model. No API keys, no per-token cost. English for now.

Vocabulary

Teach it the names it keeps missing, seeded so they come out right.

Snippets

A short trigger expands to full text. Exact-match, no guessing.

Continuous mode

Think out loud in passes. Review before anything is injected.

Usage at a glance

A local seven-day chart of words dictated and time saved.

Configurable hotkey

Push-to-talk on Fn, right Command, or right Option. Your choice.

Adaptive silence

It stops listening when you stop talking, not on a fixed timer.

Privacy that is structural, not promised.

Most apps ask you to trust a privacy policy. Ploca removes the need for trust. No code writes your audio to disk or sends your transcripts anywhere. Telemetry was never built.

Audio stays in RAM
Captured to memory, transcribed, discarded. Nothing written to disk but your settings.
No telemetry, ever
No analytics, no crash reporter, no install ID. Silent on the network.
One disclosed check
A single launch-time beta check. Headers only, no audio or usage data, with a seven-day offline grace.
Permissions it refuses
No Input Monitoring, no Screen Recording. Other tools use both for context. We do not.
Verifiable
Watch the network with a tool like Little Snitch and see the silence yourself. Read the privacy page →

Honest about where we differ.

Wispr Flow and Superwhisper are good tools with different trade-offs. Here is where Ploca stands apart, and where it does less.

ploca Wispr Flow Superwhisper
Runs fully on-device
No cloud path at all
Works offline
Local refine, no API keys
No screen or keylogger access
Tuned for Tanglish and Hinglish
Windows and mobile too
Price Free in beta About $15 / mo From $8.49 / mo

Competitor details are drawn from their public pages in mid-2026 and may change. Check their sites for current terms.

What ploca deliberately does not do

  • No cloud models, at any tier.
  • No rewriting your words into something that is not yours.
  • No per-app modes to manage. The defaults are the product.
  • No Windows, Intel Macs, or mobile, and Refine is English-only for now.

Built for people who think in sentences.

A pen's job is to write. Not to remember. Not to transmit.

A voice-to-text app should act like a pen. It should hear you and write it down, and nothing more. There are already plenty of notepads, audio archives, and second brains. Those are different products, for different jobs.

I kept looking for that pen and could not find one. I am a writer who is lazy to type, and I do not want a model generating my first draft. Every tool I tried had a trade-off I could not live with. The transcription was not good enough, the privacy was someone else's policy document, or my words were quietly training a model I would never see.

So I built Ploca for myself. Since then I have been publishing at least one essay a week, thinking out loud with Claude instead of typing, and getting thoughts down as fast as they form. The friction is gone.

If that sounds useful to you, I would like to have you in the beta.

Aasif Iqbal J. · maker of ploca

Read the five principles behind ploca →

Try it. It costs nothing right now.

Open and free until 30 August 2026, for as long as the beta runs.

We email you the link. Apple Silicon · 8 GB RAM (16 GB recommended) · macOS 13 Ventura or later. The app is about 180 MB; the first launch downloads a speech model sized to your Mac (around 1 to 3 GB), once.