Does the audio ever leave my device?

Not in local mode. Transcription runs on your machine, and the open-source code proves there's no upload step. Cloud transcription is optional, off by default, and entirely your choice to switch on.

Is this consistent with my duty of confidentiality?

Confidentiality is your professional duty, and no tool discharges it for you. A local-first architecture makes that duty easier to uphold: privileged dictation is transcribed on your device and never sent to a third party. No vendor holds client confidences, and there is no third-party processor to vet or contract for. This is not legal advice; the rules of your bar association or governing authority still apply.

Can it handle legal terminology and citations?

Yes. It runs Whisper-class models trained on a wide range of accents and 99+ languages, and the custom dictionary lets you add case names, Latin, statutes, party names and the citations your practice uses so they come out right.

Will it work in court or on the train with no signal?

Yes. Local models run entirely offline. Dictate in court, in chambers or on the train, and file the note once you're back in range. Cloud tools can't do this, because they stall the moment you leave signal.

Does it draft the letter, or just transcribe?

Both. Connect your own AI key to turn a dictated note into a letter, file note or memo. You bring the key, so the model and the data path are ones you already trust.

Yes. Unlimited local dictation, 99+ languages, all three desktop platforms: $0 forever, for every seat. Pro ($8/month) adds more cloud transcription and mobile dictation if you want them.

Dictation software for lawyers & attorneys

Speak it once. Get a drafted document. Nothing leaves your machine.

OpenWhispr turns your dictation into clean letters, memos and attendance notes on your own computer. No transcription vendor, no per-seat subscription, and it works fully offline.

Open source · 80,000+ downloads

Dictate into:

ClioiManageNetDocumentsMyCaseSmokeballMicrosoft Word

The problem with cloud dictation

Confidentiality shouldn't depend on a vendor's privacy policy.

You want dictation that drafts the letter for you. You can't have privileged material sitting on someone else's server to get there.

A stranger transcribing privileged notes.

Traditional dictation gets sent to a typing pool or an outsourced service, so someone you've never met hears the file. OpenWhispr transcribes on your own machine. No one else is ever in the loop.

Privileged material on a vendor's server.

Cloud transcription means a third party holds your client's confidences and your case strategy. OpenWhispr processes everything on your device. There is no server for any of it to sit on.

Typing is billable time you can't bill.

An hour spent drafting a letter is an hour you didn't spend on the matter. OpenWhispr drafts it from your dictation while it's fresh, so you review and send instead of type.

"Trust us" is not a confidentiality safeguard.

Closed tools ask you to take their privacy policy on faith. OpenWhispr's code is public on GitHub. Your IT or risk team can read exactly what it does, and doesn't do.

What you get

Faster drafting. Same confidentiality.

Legal dictation tools usually trade confidentiality for convenience, or bill you every month. This keeps the drafting speed and drops both: transcription and letters that stay between you, your client and your machine.

Dictation transcribed on-device

Dictate a letter, memo or attendance note into your mic. It's transcribed locally and never uploaded. You decide what's kept and when it's deleted.

Letters and memos, drafted for you

Turn spoken notes into a structured letter, file note or memo. You review every word before it leaves your desk, then paste it into Word or your document system.

Dictation wherever your cursor is

Press a hotkey and dictate straight into Word, an email or your case system. Clean, punctuated text, processed locally.

Privileged audio sent to us

None

in local mode, transcription never leaves your device

Cost per lawyer

unlimited local dictation, the whole firm, forever

Setup takes

5 min

from download to your first dictated letter

How it works

A letter drafted before you move to the next matter.

Most legal dictation lives in the cloud or a typing pool. This lives on your machine: no account to start, no credit card, nothing stored on anyone's server, including ours.

Download for free.

Mac, Windows or Linux. Pick a local model during setup.

Dictate the note.

Speak your letter, memo or attendance note, and it's transcribed on your device.

Review, file, delete.

Edit the draft, paste it into Word or your document system, and delete the audio. You control all of it.

No convincing needed

10 reasons lawyers choose OpenWhispr

Choosing a dictation tool is a confidentiality decision before it's anything else. Here are the facts, and your IT or risk team can verify every one in the repo.

Audio never leaves your device

Dictation and drafts are processed locally. There's no upload step in the code.

Free for the whole firm

Unlimited local dictation at $0, every seat, forever. No per-fee-earner licence to renew.

Nothing goes to a typing pool

No outsourced transcriber ever hears the file. The dictation stays between you and your machine.

Works fully offline

Court, chambers, a client's office, the train. No signal required, so it never stalls mid-dictation.

Dictate into Word or any case system

A system-wide hotkey drops clean text wherever your cursor is: Word, Clio, iManage, an email.

Letters and memos, not just transcripts

Connect your own AI key to turn dictation into a drafted letter, file note or memo.

You control storage and deletion

Recordings and transcripts live as files on your machine. Keep, encrypt or delete on your terms.

Open source, auditable by anyone

Your IT or risk team can read every line on GitHub. No faith required.

Handles legal terminology

A custom dictionary learns case names, Latin terms, statutes and the citations your practice uses.

99+ languages

Take instructions in the language your client actually speaks, transcribed locally.

Before you download

The questions lawyers ask first.

Straight answers on confidentiality, cost and accuracy. If yours isn't here, ask us in Discord. We reply within 24 hours.

What users say

Built by people who don't want to be recorded either.

From our Discord, GitHub and inboxes, the same instinct that matters under privilege.

Privileged files on a server

In local mode the audio never leaves your device. Nothing is stored on a server, and nothing is sent to a transcriber.

Started using OpenWhispr with my local models and hardware. I have to say, this is better than typing.

0xSero@0xSero

I switched to voice input for my Claude Code chats. Even when I stumble and rephrase mid-sentence, the transcription comes out clean and polished.

j3iiifn@j3iiifn

I needed a local model for when I'm travelling or have no WiFi, and this perfectly solves it. The UI and performance are great.

Gabe@gabe__perez

Pricing

Free forever.
Upgrade when you want more.

Compare OpenWhispr plans for lawyers
	FreePopular $0No card details needed Loading...	Pro $6.67/user/mo$80/user billed annually Start with Pro	Business $13.33/user/mo$160/user billed annually Start with Business
Best for	Lawyers who want free, private, offline dictation and are fine with a quick local setup	Lawyers who want easy, reliable cloud transcription	Firms and teams documenting at volume
Main reason to choose	Free offline dictation, with privileged audio staying on your device	Unlimited cloud transcription without managing local models or keys	Unlimited recordings plus advanced workflow features for a team
Offline speech-to-text	Included	Included	Included
Cloud speech-to-text	2,000 words/week via OpenWhispr Cloud, or unlimited using your own API keys	Unlimited OpenWhispr Cloud speech-to-text	Unlimited OpenWhispr Cloud speech-to-text
Meeting recordings	5 hours/month	20 hours/month	Unlimited
Privacy & data handling	Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored.	Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored.	Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored.
Setup experience	Hands-on: install app, choose local models, optionally add API keys	Easy: install app, upgrade, use unlimited cloud speech-to-text	Moderate: configure users, Agent mode, and data workflows
Advanced features	Custom dictionary improves names/terms 100+ languages multilingual speech-to-text	Custom dictionary improves names/terms 100+ languages multilingual speech-to-text Device sync use across devices Mobile companion app dictate on mobile API / MCP access connect tools/workflows	Custom dictionary improves names/terms 100+ languages multilingual speech-to-text Device sync use across devices Mobile companion app dictate on mobile API / MCP access connect tools/workflows Agent mode automate actions Chat over your data ask about files/transcripts
Team management	None	None	Basic team / workflow use
Support	Community support	Email support	Priority support

Need SSO, compliance features, admin controls, or dedicated support for a larger team?

We also offer a custom Enterprise plan with managed onboarding and tailored features.

Talk to us

Built in the open

Some conversations are privileged. We built for those.

OpenWhispr started with a simple objection: the notes that carry a client's confidences shouldn't have to pass through a stranger's server to become a letter.

We build in public. Every release and every line of code is on GitHub, where 3,100+ engineers have starred, forked and audited the project. When we say the dictation stays local, that's not a promise in a privacy policy. It's a property of the code, and anyone in your firm can verify it.

And if anything breaks, you talk to the people who built it, in Discord.

Free · open source · local-first

Your dictation stays between you, your client and your machine.

Download OpenWhispr and your next letter gets dictated, drafted and filed. On your computer, nowhere else.

Takes 5 minutes to set up. If it doesn't work, we'll fix it with you in Discord. Free forever on Mac, Windows & Linux.