LocalScribe

AI-assisted clinical documentation

Private by Design

No data sent to servers

Runs locally on your computer

Time Savings

Notes in seconds

Reports in minutes

Supports HIPAA workflows

Built for local documentation workflows

Clinician-built

Built around real note and report work

See How LocalScribe Works

Clinical content you type

Fight w/ partner this weekend. Slept 4 hrs. Tearful at start. Ambivalent about boundary-setting call tonight. Practiced grounding. Identified all-or-nothing thinking. Boundary-setting call tonight. Denies SI/HI.

Built by John Britton

A clinician-built project from someone still in training.

John Britton is a clinical psychology doctoral student focused on how mental health professionals can participate in shaping how artificial intelligence enters clinical practice. His interests sit at the intersection of psychology and technology, with an emphasis on ethical, transparent, and clinically responsible use rather than automation for its own sake.

I built LocalScribe while learning to build software myself. Part of that was trying to build my skills and resume. Part of it was that I had a good idea for a local-first clinical tool and wanted to make it real.

That is also part of why the site is more personal now. I want clinicians to see what it looks like when someone still in training builds, tests, and shares a tool in public while staying clear about what it can and cannot do.

Read more about John and the project.

Download here for free use.

Windows uses Microsoft Store. macOS is a direct download.

What LocalScribe Does

Drafting & Templates

Inputs & Workflow

Editing & Output

Libraries & Control

Built for the Whole Care Team

Mental health and allied health clinicians share the same documentation burden. LocalScribe adapts to your specialty, not the other way around.

Custom Terminology Library

Start with ready-made specialty terms, then make them your own. You can use starter packs for areas like music therapy, physical therapy, school psychology, and more.

Flexible Template Builder

Build structured frameworks for your discipline: functional goal SOAP notes, ADL evaluation formats, session plans, or specialized assessment structures. Your templates, your clinical logic.

Local-first privacy and compliance support

Runs on your device

Drafting stays local instead of routing clinical content to a remote AI service.

Works offline after setup

Use LocalScribe without internet once the app and model are installed.

Audit tools built in

Encrypted logs, auto-lock, biometric access, and timestamped audit trails.

Designed to stay in your environment

Clinical drafting is designed to stay on your device during normal use.

See privacy details

What to know

  • Drafting stays on-device: Your note is processed on your computer, not sent to a remote AI service.
  • Works offline after setup: Once installed, LocalScribe can keep drafting without internet access.
  • Review tools are built in: Audit trails and a downloadable privacy report support internal review.

Drafting Speed by Hardware

What to expect on different systems

These timing examples are meant to set expectations, not promise exact results. Performance depends on your hardware, available memory, and other open apps.

Daily SOAP Note ~20 sec - 1.5 min+
Clinical Letter ~30 sec - 3 min+
Complex Report / Eval ~1 min - 6 min+

See estimated drafting times by hardware tier

Daily notes, letters, and reports across faster and lighter systems.

Document Type Fast (Mac / Windows GPU) Windows (CPU only) Older (CPU only)
Daily SOAP Note
Typical: ~20-80 sec
Typical: ~30 sec - 2.5 min
Typical: ~1-3.5 min
Clinical Letter
Typical: ~30 sec - 2.5 min
Typical: ~1-5 min
Typical: ~2-8 min
Complex Report / Eval
Typical: ~1-6.5 min
Typical: ~2-14 min
Typical: ~4-24 min

*Times vary by length of recording or shorthand input.

More available RAM and a stronger CPU or GPU generally improve drafting speed, especially for longer reports.

What is in the app

LocalScribe Features

Drafting & Templates

  • Progress notes: SOAP, DAP, BIRP, Intervention-Response, and Simple Note
  • Reports and letters: intake reports, treatment plans, termination summaries, session summaries, professional letters, and referral letters
  • Evaluation workflows: psychological evaluations, neuropsychological evaluations, school psychological reports, and test interpretation
  • Custom templates with your own sections, prompts, and documentation logic
  • Generate follow-up documents from an existing note without starting over

Capture & Inputs

  • Clinical shorthand drafting from rough notes, pasted text, or partial documentation
  • Live dictation for real-time note capture directly on your device
  • Session recording with full transcription for fuller draft context
  • Attachments for PDF, DOCX, XLSX, TXT, and audio files
  • Offline-friendly workflow after setup for schools, homes, and community settings

Customization & Libraries

  • Writing style controls plus custom instructions that shape tone, structure, and emphasis
  • Terminology libraries for specialty language, abbreviations, and recurring phrasing
  • Test measures and reference libraries for report-heavy workflows
  • Template-specific prompts so each section can follow your clinical logic
  • Built-in AI models you can switch between based on speed and task fit

Refine, Export & Controls

  • Refine and regenerate drafts without restarting the whole note
  • Edit a draft by telling LocalScribe exactly what to change, like make it shorter, simplify it, or rewrite one section
  • De-identification tools for replacing PHI before export
  • Password-protected PDF export and version history
  • Built-in self-diagnostics and local troubleshooting tools
  • Local-first design so drafting, transcription, and attachment processing run on your device instead of a remote server
  • Only your saved setup is stored locally, and LocalScribe does not store your clinical input or generated output or use that data to train AI models

System Requirements by Platform

Runs on Windows 10/11 and macOS 12+. Downloads are about 500 MB; the unpacked macOS app is about 1 GB. CPU-only supported; GPU optional for speed. Plan on at least 8 GB RAM, with 12 GB+ recommended for smoother drafting and 16 GB+ ideal for heavier report workflows.

Performance also depends on available memory and other open apps.

See detailed system requirements

Windows and macOS minimum and recommended specs.

macOS (64-bit)

Officially supported on macOS 12+ (Monterey and newer).

LocalScribe
Minimum
  • Any Apple Silicon or Intel Mac that can run macOS 12+
  • 8 GB RAM
  • Disk: about 500 MB download, about 1 GB unpacked on disk
Recommended
  • Apple Silicon (M1 or newer) recommended
  • 12 GB+ memory, with 16 GB+ ideal for longer reports

Current Mac builds are direct downloads. The app may show an unknown developer warning on first open. If you are comfortable proceeding, you can right-click the app and choose Open, or allow it in Privacy & Security after the first launch attempt.

Windows (64-bit)

Officially supported on Windows 10 (22H2)+ and Windows 11.

LocalScribe
Minimum
  • Any 64-bit Intel/AMD CPU (newer is better)
  • 8 GB RAM
  • Disk: about 500 MB download
Recommended
  • Recent Intel/AMD CPU (6+ cores recommended)
  • 12 GB+ RAM, with 16 GB+ ideal for heavier report workflows
  • Optional dedicated GPU for faster drafts and exports
Download here for free use.

Windows uses Microsoft Store. macOS is a direct download.

Frequently Asked Questions

How do I get started?

Download the app, open it, and install a writing model from Settings. Once a model is selected, you can type or paste clinical material, choose a template, and create your first draft.

On macOS, the current direct-download build may show an unknown developer warning on first open. If you are comfortable proceeding, you can right-click the app and choose Open, or allow it in Privacy & Security after the first launch attempt.

What hardware do I need?

See the System Requirements section for OS-specific minimum and recommended specs. In general, LocalScribe can run on 8 GB RAM systems, 12 GB+ is a better everyday target, and 16 GB+ is ideal for longer report workflows. GPU is optional and improves speed.

How fast will it write my notes (tokens per second)?

Drafting speed is measured in Tokens Per Second (tok/s), where one token is roughly 3/4 of a word. A modern Mac or Windows PC with a dedicated GPU drafts very quickly (35-75 tok/s). A standard CPU-only laptop runs slower (7-25 tok/s), taking a few minutes per draft. Complex reports will always take longer than daily progress notes.

How does local processing change the workflow?

With a cloud AI tool, note content has to travel to someone else's servers for processing. LocalScribe is built around a different path. Drafting, transcription, and attachment handling are designed to happen on your own computer instead.

That does not settle HIPAA by itself, because the full workflow still depends on the clinician, the local environment, and where exported material goes next. It does remove one major category of exposure that comes with routing sensitive content through an outside service.

Does LocalScribe support HIPAA workflows?

LocalScribe was built for local clinical drafting workflows where privacy, access control, and auditability matter. It includes local processing, audit logs, auto-lock controls, encrypted exports, and a privacy report that can support an internal review process.

That is different from saying a clinic is automatically HIPAA compliant just because the app runs locally. Compliance still depends on the setting, policies, device security, storage, exports, and the clinician's own workflow.

Can it work without internet?

Yes. After the app and the models are installed, LocalScribe can run offline for drafting workflows. Internet may still be needed for setup steps, updates, or downloading optional components.

How do I set up LocalScribe's AI?

Install the app, open it, and create your username. Then open Settings in the left navigation, click Models, and download a writing model that fits your computer. Once one is downloaded and selected, go back to the main screen, enter a few notes, choose a template, and click Create New Draft for your first generation.

If you want voice features, open the Settings modal and go to Dictation. Set the Dictation Model for live dictation. If you plan to use Session Recording or Audio Attachments, choose the model for those there too.

Does my data ever leave my device?

No. All AI inference happens locally. Audio, text, and generated notes stay on your machine. You control what you copy, export, or share.

Is LocalScribe safe for client or patient data?

LocalScribe is built with a local-first design so drafting, transcription, and attachment processing run on your device instead of a remote server. The only reusable content the app keeps locally is what you intentionally save for later, such as custom templates, custom terminology, and writing styles. Session materials are designed to clear when you close the note or app.

Is any data stored or used to train an AI model?

LocalScribe stores only your saved setup locally on your device, including things like custom templates, custom terminology, writing styles, and app settings. It does not store your clinical input or generated output, and it does not use any of that data to train AI models.