LipConfirm
The next generation of autocorrect.
Autocorrect that uses your lips—or a quiet whisper—to help find the word you meant.
Typing on small phone keyboards remains a source of errors and frustration. LipConfirm combines keystrokes with real-time lip cues or whisper-level audio to help autocorrect recover the intended word—even when the typing is garbled or ambiguous.
All 30 claims allowed · U.S. Patent No. 12,737,540 scheduled to issue September 15, 2026.
Lip-assisted correction
Silently mouth the intended word while typing. Camera-captured lip cues help autocorrect distinguish between possible corrections.
Whisper-assisted correction
Quietly whisper the intended word while typing. Microphone-captured audio helps autocorrect distinguish between possible corrections, without using a camera.
Why Now?
Even LLM-informed autocorrect can struggle when mobile typing produces garbled or ambiguous words. LipConfirm adds evidence from the user—a silent mouth cue or a quiet whisper—to help recover the intended word.
How it works
Preliminary desktop demos are available for both lip-assisted and whisper-assisted correction. The videos below show lip-assisted correction.
Capture
With your permission, lip mode captures mouth movement through a camera; whisper mode captures quiet audio through a microphone. Either signal, or both, can be combined with typing. The architecture supports on-device processing and discarding raw sensor data after feature extraction or scoring.
Multimodal fusion
LipConfirm combines typed input with lip cues, whisper-level audio, or both to improve correction ranking and candidate recovery. The architecture can use heuristic scoring, on-device ML, or learned multimodal fusion depending on the implementation.
Seamless correction
When confidence clears a threshold, LipConfirm can replace the garble without interrupting your flow. In lower-confidence cases, the normal suggestion bar remains available as a fallback.
What the demos show
- Messy input, clear intent. Fast, imperfect typing that normally fails to suggest the right word.
- Lip or whisper-guided selection. As the user silently mouths or quietly whispers the intended word, LipConfirm combines lip cues or whisper audio with the typed string to help select the intended correction.
- Typing stays primary. This is not voice dictation or standalone lipreading. The user keeps typing normally; lip movement or whisper audio provides an additional signal of intent.
- Note: The lip video panel is a behind-the-scenes visual aid for lip-assisted correction. The same correction workflow can use whisper audio instead, without a camera. An integrated keyboard need not display the camera feed.
Preliminary desktop demos are available for both lip-assisted and whisper-assisted correction. The videos below show lip-assisted correction.
What the demos show
- Messy input, clear intent. Fast, imperfect typing that normally fails to suggest the right word.
- Lip or whisper-guided selection. As the user silently mouths or quietly whispers the intended word, LipConfirm combines lip cues or whisper audio with the typed string to help select the intended correction.
- Typing stays primary. This is not voice dictation or standalone lipreading. The user keeps typing normally; lip movement or whisper audio provides an additional signal of intent.
- Note: The lip video panel is a behind-the-scenes visual aid for lip-assisted correction. The same correction workflow can use whisper audio instead, without a camera. An integrated keyboard need not display the camera feed.
Strategic Partners & Investors
From desktop demos to mobile prototype
LipConfirm has preliminary desktop demos of both lip-assisted and whisper-assisted autocorrect. The next milestone is completing our mobile prototype, running real-user tests, and optimizing for private on-device operation.
Built for existing input stacks
LipConfirm is designed as an auxiliary correction layer that can work with existing keyboard, autocorrect, spell-checking, and language-model infrastructure, rather than requiring a full rewrite of the text-entry stack.
High-value use cases
LipConfirm is especially relevant to mobile keyboards, accessibility, quiet or private input, wearables, smart glasses, and AR/XR text entry, where small keyboards and limited feedback make correction harder.
LipConfirm is open to strategic licensing, integration, SDK partnership, and investment discussions with companies and investors focused on next-generation human-computer input. A short non-confidential overview and preliminary desktop demos of both modes are available for serious strategic or investment inquiries.
Patent & IP
All 30 claims allowed. U.S. Patent No. 12,737,540 is scheduled to issue September 15, 2026. The allowed claim set addresses lip-assisted correction, shared multimodal operation, and a camera-free whisper-assisted pathway that generates textual proxies for an existing spell-correction engine.
Two U.S. continuation applications are pending, seeking additional protection for lip- and whisper-assisted autocorrect. One has been granted Track One prioritized examination.
PCT/US2026/035963 is pending. The USPTO, acting as the International Searching Authority, found all 30 PCT claims novel, inventive, and industrially applicable, with no category X or Y prior-art citations.
FAQ
Is this just voice dictation?
No. Typing remains the anchor. A quiet whisper or silent mouth cue helps disambiguate the intended correction; neither full dictation nor standalone lip reading is required.
Does this require the internet or cloud processing?
LipConfirm is designed to support fully on-device correction, without sending raw mouth-region frames or audio to the cloud. Raw sensor data can be discarded after feature extraction or scoring.
Will this drain battery or slow down typing?
LipConfirm is designed for lightweight, on-device operation and for activation only during relevant typing intervals. Final battery impact will depend on the implementation and device settings.
Does LipConfirm require a camera?
No. Lip-assisted correction uses camera-captured mouth movement, while whisper-assisted correction uses quiet audio from a microphone and does not need camera input. Sensor capture can be limited to relevant text-entry intervals with user permission.
How is this different from existing autocorrect?
Existing autocorrect primarily relies on typed characters, keyboard geometry, context, and language-model predictions. LipConfirm adds another signal: lip movement or a quiet whisper that can help identify what the user intended to type, especially when typed input is garbled or ambiguous.
Do I need to perfectly mouth the words?
No. Lip-assisted correction uses cues such as syllable counts and mouth shapes alongside your typed input. The goal is to use enough visual information to resolve ambiguity—not to recognize every word from lips alone.
Does either mode replace typing?
The core experience is typing-first: both modes help resolve ambiguity in ordinary keyboard input, rather than requiring standalone lip reading or full dictation. The broader architecture also supports other combinations of active input channels.
Can I use lip and whisper modes separately?
Yes. Either can provide the extra evidence alongside typing. Lip mode uses camera-captured mouth movement; whisper mode uses microphone-captured quiet audio and does not require a camera. The architecture also supports combining both signals.
How is AI used here?
LipConfirm can use on-device ML models to combine typed input with lip cues, whisper-level audio, or both. Existing autocorrect primarily relies on typed characters, keyboard geometry, context, and language-model predictions. LipConfirm adds lip or whisper evidence that can help rerank candidates, recover missed candidates, or improve confidence in the intended correction.
Does the user need to train or calibrate the model?
LipConfirm is designed to minimize or avoid required calibration in ordinary use, with optional personalization available to improve accuracy over time.
How much accuracy improvement does LipConfirm provide?
LipConfirm is designed to recover missed cases where ordinary autocorrect fails because the intended word is ambiguous, low-ranked, or absent from the suggestion list. Preliminary desktop demos cover both lip-assisted and whisper-assisted approaches. Real-world accuracy will depend on implementation, device conditions, and user behavior.
Is LipConfirm only for mobile phones?
Mobile keyboards are the primary target because fast typing on small screens, especially in portrait mode, causes the most frustration today. But LipConfirm is designed as a general fusion layer that can work in any typing environment — including tablets, laptops, and even wearable devices.
Will I still see suggestion lists?
When confidence is high, LipConfirm can automatically insert the intended correction. When confidence is lower, the suggestion bar can offer candidates informed by both typed input and the enabled lip or whisper signal.
Is this patented?
All 30 claims of the U.S. parent application have been allowed, and U.S. Patent No. 12,737,540 is scheduled to issue September 15, 2026. Two U.S. continuation applications and a PCT international application are pending. One continuation has been granted Track One prioritized examination. See Patent & IP for details.
Contact
Email: hello@lipconfirm.com
LipConfirm was conceived and developed by Andre Persidsky, a multidisciplinary engineer and inventor with experience building, patenting, and licensing technology. Andre has previously licensed technology to commercial partners including Spotify, and has led hardware/software health-technology projects in collaboration with external research institutions.