Get the newsletter
Apple · AI / ML · Filed Jan 12, 2026 · USPTO published Nov 19, 2026 · This week's release

Apple Files Patent for Fixing Dictated Messages by Just Talking to Your Phone

Fixing a dictated message usually means tapping around the screen. This Apple patent application describes saying 'Change the third Jon to J-O-H-N' and having your device simply do it.

A smartphone digital assistant links a person speaking to network servers and messaging services. Drawing from patent filing US 2026/0369269 A1.
A smartphone digital assistant links a person speaking to network servers and messaging services.All 25 drawings ↓
Publication number
US 2026/0369269 A1(US20260369269A1)
Applicant
Apple Inc.
Filed · Published
Jan 12, 2026 · Nov 19, 2026
Inventors
Timothy S. PAEK, Viet Huy LE, Susumu HARADA, Leena A. PANCHMATIA, Felicia W. EDWARDS, Livi ZHU, Mahesh KRISHNAMOORTHY, Kevin LUIKENS, Leo LIU, Muktan Rahulkumar PATEL, Jin WANG
Status when we published
Waiting for an examiner
Document
20 claims
US classification
704/257
Parent application
Claims priority from a provisional application 63808519 (filed May 19, 2025)

What Apple's voice-editing patent actually does

A man dictates a text to his friend, and his phone writes 'John' when the friend spells his name 'Jon.' Fixing it means tapping the screen, dragging the cursor and retyping, which is the work talking was supposed to save him from.

Apple's patent application describes fixing that by speaking instead. You could say, 'Change the third Jon to J-O-H-N,' or 'Change except to accept, like accepting a deal.' The device works out which word you mean, even when it appears several times, and can highlight the options so you can pick one.

Behind the scenes, your request goes through lighter software first. If that cannot handle it, a large language model (the type of AI behind chatbots) steps in and makes the edit.

From the filing · CLAIM 1
… receiving a speech input including a command to modify a target set of characters, wherein the command corresponds to a natural language request; processing the command using one or more first models …

Translation: The system listens to your spoken edit request and tries to process it using standard tools.

How a quick check decides when the AI steps in

The patent describes a voice-editing setup with two tiers. While text is on screen, you speak a command in everyday language (the filing calls it a natural language request) asking to change part of that text. The device first runs the command through one or more first models, the lighter software meant for straightforward requests.

Then it checks whether that first pass met a completion criteria (in plain terms, did the quick tools understand the request and finish the job?). In the dependent claims, the check passes when the quick models can pinpoint the text you mean and you want to edit it, or when you dictate new content relative to existing text. It fails when you dictate content with no reference to existing text. A failed check sends the command to second models, which include a large language model, and those make the change.

The filing also describes extras:

  • Clues like a spelling or a description, such as 'accepting a deal,' to pick the right word
  • Choosing a specific repeat, like the 'third Jon,' or highlighting each match so you can tap the right one
  • Fixing punctuation and the text around it after an edit
  • Finding the target from where you are looking, or from text read aloud to you
  • A disfluency filter that strips repeated words, restarted phrases and spoken self-corrections from dictation
From the filing · THE ABSTRACT
… processing the command using one or more second models, wherein the one or more second models include a large language model, and modifying the target set of characters using the one or more second models.

Translation: If standard tools fail, a large language model steps in to fix your text.

What this means for dictating on your iPhone

Dictation is already decent at getting words onto the screen. Fixing them is where many people give up and reach for the keyboard. This approach aims at that gap, so you could correct a name or a misheard word by saying so, which would help when your hands are busy or your screen is small, like a watch.

The filing does not explain why it uses two tiers, but the split lets simple fixes stay with lighter tools while the heavier AI model is saved for harder requests. It lists iPhone, iPad, Apple Watch and earphones among its example devices, so the idea is meant to work across Apple's lineup.

That makes this Apple's third filing in our Enterprise AI coverage since June, joining one on location-aware task lists and one on AI video reframing.

Source: US 2026/0369269 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Apple patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 25 sheets

25 drawing sheets from US 2026/0369269 A1 · click any drawing to enlarge

Connecting phones to cloud servers for voice assistance, drawing sheet 1 from US 2026/0369269 A1
Sheet 1 Connecting phones to cloud servers for voice assistance
Hardware and software components inside a smartphone, drawing sheet 2 from US 2026/0369269 A1
Sheet 2 Hardware and software components inside a smartphone
Touch and gesture management inside an application, drawing sheet 3 from US 2026/0369269 A1
Sheet 3 Touch and gesture management inside an application
External sensors and controls on a touchscreen phone, drawing sheet 4 from US 2026/0369269 A1
Sheet 4 External sensors and controls on a touchscreen phone
Internal parts of a computer with a separate trackpad, drawing sheet 5 from US 2026/0369269 A1
Sheet 5 Internal parts of a computer with a separate trackpad
How an app trades data with the operating system, drawing sheet 6 from US 2026/0369269 A1
Sheet 6 How an app trades data with the operating system
Software layers that let apps request system services, drawing sheet 7 from US 2026/0369269 A1
Sheet 7 Software layers that let apps request system services
Data flow between an app and core system functions, drawing sheet 8 from US 2026/0369269 A1
Sheet 8 Data flow between an app and core system functions
Show the other 17 sheets
A smartphone home screen showing apps that can receive dictation, drawing sheet 9 from US 2026/0369269 A1
Sheet 9 A smartphone home screen showing apps that can receive dictation
Controlling a screen menu using gestures on a touchpad, drawing sheet 10 from US 2026/0369269 A1
Sheet 10 Controlling a screen menu using gestures on a touchpad
A smartwatch case designed to run voice commands, drawing sheet 11 from US 2026/0369269 A1
Sheet 11 A smartwatch case designed to run voice commands
Internal parts and sensors powering the wearable device, drawing sheet 12 from US 2026/0369269 A1
Sheet 12 Internal parts and sensors powering the wearable device
Memory components that store voice recognition and assistant software, drawing sheet 13 from US 2026/0369269 A1
Sheet 13 Memory components that store voice recognition and assistant software
How the voice assistant turns speech into actions, drawing sheet 14 from US 2026/0369269 A1
Sheet 14 How the voice assistant turns speech into actions
Mapping out connections between topics like reservations and reminders, drawing sheet 15 from US 2026/0369269 A1
Sheet 15 Mapping out connections between topics like reservations and reminders
The AI model that turns user requests into text answers, drawing sheet 16 from US 2026/0369269 A1
Sheet 16 The AI model that turns user requests into text answers
How the AI turns spoken edit commands into text changes, drawing sheet 17 from US 2026/0369269 A1
Sheet 17 How the AI turns spoken edit commands into text changes
Asking your phone to swap punctuation marks in a draft, drawing sheet 18 from US 2026/0369269 A1
Sheet 18 Asking your phone to swap punctuation marks in a draft
Telling the phone to erase a specific phrase, drawing sheet 19 from US 2026/0369269 A1
Sheet 19 Telling the phone to erase a specific phrase
Watching deleted words vanish before continuing dictation, drawing sheet 20 from US 2026/0369269 A1
Sheet 20 Watching deleted words vanish before continuing dictation
Correcting a misspelled name by spelling it out loud, drawing sheet 21 from US 2026/0369269 A1
Sheet 21 Correcting a misspelled name by spelling it out loud
Explaining what a mistranscribed word actually means, drawing sheet 22 from US 2026/0369269 A1
Sheet 22 Explaining what a mistranscribed word actually means
Selecting which duplicate word to replace using speech, drawing sheet 23 from US 2026/0369269 A1
Sheet 23 Selecting which duplicate word to replace using speech
Replacing the targeted word after your spoken instruction, drawing sheet 24 from US 2026/0369269 A1
Sheet 24 Replacing the targeted word after your spoken instruction
How the phone chooses which AI model fixes your message, drawing sheet 25 from US 2026/0369269 A1
Sheet 25 How the phone chooses which AI model fixes your message
Patent filing page

Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.