GET LockedIn Flow for Mac

Get LockedIn Flow.Private dictation for your team’s Macs.

Request a build for your team. We reply by email and plan setup with you. Free under the MIT License, for personal and commercial use.

Apple siliconmacOS 15 or later≈484 MB modelNo account

Fig. 01 — Menu bar panel · 332 pt · ready

01 Team build

Request a build for your team.

Tell us about your Macs and how you’ll deploy. We take it from there.

Team build requestReply by email
Platforms your team uses
LockedIn Flow runs on Apple silicon Macs with macOS 15 or later.
How you plan to deploy, the apps your team dictates into, your timing.

Keep it general. Never include passwords, access tokens, dictated text or other sensitive data.

We reply to your work email.

What happens next

  1. You send it

    One short form.

    Work email, company, seats and a note. No account to create.

  2. We reply

    By email, from LockedIn Labs.

    We plan the build and setup with you, and share the threat model, security policy and SBOM for your review.

  3. You deploy

    Your signature. Your MDM.

    Sign with your own Developer ID, pre-stage the verified speech model, and roll out with your own tools.

  4. Your team dictates

    Press ⌃⇧Space. Speak.

    Recognition runs on the Mac, and the words are pasted at the cursor. No internet needed once the model is installed.

02 Requirements

What your Macs need.

An Apple silicon Mac, macOS 15 and room for one speech model. No account, no license key, no activation.

MacApple siliconRecognition runs through Core ML.
SystemmacOS 15Or later. Optional Apple Intelligence features need macOS 26.
Speech model≈484 MBInstalled once. Verified before it loads.
AccountNoneNo trial, no word cap, no activation.
Datasheet — after installPer Mac
Network
None needed once the model is installed. The app never downloads models, checks for updates, sends telemetry or calls a hosted service. Its speech library’s downloader is switched off before any model loads.
Permissions
Microphone, and Accessibility to type. Nothing else. Copy only mode works without Accessibility access.
Models
Parakeet TDT v3, 25 European languages. Optional English Precision model: about 614 MB more. Every model file is checked against a SHA-256 compiled into the app.
Optional
Contextual cleanup, translation and meeting notes use Apple’s on-device model on macOS 26 with Apple Intelligence. Dictation itself doesn’t need them.
License
MIT. Free for personal and commercial use. Enterprise deployment, terminology, maintenance, validation and support are optional services.
Ships with
A software bill of materials and a provenance record with every packaged build.

03 Before you ask

Straight answers.

What does it cost?

LockedIn Flow is free under the MIT License, for personal and commercial use. No trial, no word cap, no activation, no account. Enterprise deployment, terminology, maintenance, validation and support are optional services.

Does it need the internet?

Not once the speech model is installed. The app never downloads models, checks for updates, sends telemetry or calls a hosted service. Its speech library’s downloader is switched off before any model loads. The only download is the speech model, once, outside the app.

How does it reach our managed Macs?

Sign and notarize with your own Developer ID, pre-stage the verified speech model in a root-owned location, pre-approve Accessibility with a PPPC profile, and deploy with your own MDM. Removal is fully documented. See enterprise deployment.

Can we review the source?

Yes. Evaluating organizations can review the full source on request. The threat model, security policy and SBOM are available for your review.

Which languages does it recognize?

25 European languages, with no language picker needed. The cleanup rules are written for English; turn cleanup off for other languages.

SEC Evaluating first?

Review the security architecture.

Five single-purpose libraries, one entitlement, no networking code in the app’s own source. Read how it keeps audio on the Mac.