Skip to content

Yap for lawyers

Dictation software for lawyers that keeps client matters on your computer.

Dictate briefs, letters, file notes and emails straight into Word, Outlook or your practice management software. Yap recognizes your speech on your own Mac or PC: the audio is never uploaded, never stored by us and never used to train a model.

Mac, Windows, iPhone and Android. $6.90 USD a month or $69 USD a year per person. 3 days free with a free account, no card, then a 10-day trial with a card.

What the opinions ask

Know where the audio goes.

  • ABA Formal Opinion 512 says lawyers must make reasonable efforts to prevent inadvertent or unauthorized disclosure of, or unauthorized access to, information relating to a client's representation. Source
  • ABA Formal Opinion 512 says that self-learning AI tools, by their nature, raise the risk that one client's information is disclosed to others. Source
  • ABA Formal Opinion 512 concludes that informed consent is required before client information is entered into self-learning generative AI tools whose outputs could disclose it. Source
  • ABA Formal Opinion 512 says a general clause in an engagement letter is not enough to obtain the informed consent needed before using generative AI with client information. Source

State bars add their own guidance: Florida Ethics Opinion 24-1 recommends obtaining the affected client's informed consent before using a third-party generative AI program that would expose confidential information. Source

With Yap, the vendor side of that question does not arise: recognition happens on your computer, nothing you say reaches us, and nothing learns from it. This is not legal advice; your jurisdiction’s rules and your firm’s policy decide what is reasonable.

In the documents you already use.

Place the cursor, hold Fn on a Mac or Ctrl + Win on Windows, speak, and let go: the text appears with punctuation, in any app.

Nothing leaves the computer.

No audio upload, no cloud transcription, no AI rewriting step. Your dictation history stays on your computer, where you can delete it. Read our privacy policy.

Mac, PC and phone.

One subscription covers Mac, Windows, iPhone and Android, so a note dictated on the train and a letter dictated at the desk use the same account.

Being fair

When another tool fits better.

  • You need a trained legal vocabulary. Yap has no custom dictionary. Dragon sells a legal edition for Windows (Dragon Legal 16).
  • Your firm sends recordings to transcriptionists. Yap is for live dictation into your own documents, not for routing recordings to a typing pool. For a recording you already have, our free audio to text tool transcribes it in your browser.
  • You want AI to draft for you. Yap writes down what you said, cleaned up lightly; it does not rewrite or summarize.

Questions.

Does Yap send my dictation to a server?
No. Speech recognition runs on your Mac or Windows PC. The audio is not uploaded to a transcription service and is not stored by us. Finished text is kept in a local history on your computer, where you can copy or delete it.
Does Yap learn from what I dictate?
No. Yap recognizes speech with a fixed model on your computer and does not use your words to train or improve anything. It has no AI rewriting step that would send your text to a language model.
Does it work in Word, Outlook and our practice management software?
Yes. Yap types into whatever app your cursor is in. Hold Fn on a Mac or Ctrl + Win on Windows, speak, and let go.
Is on-device dictation enough to meet my duty of confidentiality?
That depends on your jurisdiction and your firm's policies; this page is not legal advice. The ABA says what counts as reasonable efforts depends on a set of factors rather than a fixed rule. Keeping the audio on your own computer removes the question of what a dictation vendor does with it.

More on the rules, state by state: Dictation for lawyers: privilege and confidentiality.

From the library

Speech to Text Privacy: Where Your Voice Goes

Dictation is only as private as the place your voice is processed and the rules of whoever processes it. On-device recognition keeps the audio on your hardware, while cloud recognition sends it to a server that may store it, train models on it or let people review it. Voice is personal data everywhere and biometric data when it identifies you, so privacy laws, HIPAA, legal ethics rules and recording consent statutes all apply, and the reliable way to dictate privately is on-device recognition with history, training and sharing settings switched off.