Direct dictation into almost any suitable Windows input field
LPS Software · Local AI Productivity
LPS Windows Diktat
In preparationLocal AI-assisted speech recognition with direct F9 dictation into Word, Outlook, browsers and other applications.
The current product build 0.9.8 is being prepared for public release.
Purpose
The product in its working context.
LPS Windows Diktat transfers spoken text directly into the previously active Windows application and combines high recognition quality with a simple global F9 workflow.
Core value
Place the cursor, press F9, speak and press F9 again: the fully recognised text is inserted into the target application. An optional live/streaming mode is also available.
Key benefits
Concrete value rather than a feature list.
Quality mode with large-v3 plus optional live/streaming mode
Local processing after model installation with automatic German/English handling
Key capabilities
From the model to a usable result.
- Global F9 start and stop directly in the target application
- Complete transcription in quality mode
- Optional live/streaming dictation with continuous insertion
- Automatic language handling for German and English
- Review mode for corrections before insertion
- Tray status for ready, recording and processing
- Desktop/NVIDIA CUDA profile for high performance
- CPU/Turbo profile for systems without NVIDIA graphics
- Local model storage and reuse of existing models
- Protection against rare repetition loops
Applications and target groups
For professional analysis and design tasks.
Professional Writing
Dictate longer texts, emails and documents without changing applications.
Teaching & Research
Capture manuscripts, feedback and notes efficiently.
Accessible Workflows
Reduce keyboard input and complement workflows with speech control.
Application views
Visual product views are being prepared.
Real application screenshots will be added after visual approval.
System requirements
Local and controlled use.
- Windows 11
- Desktop profile: NVIDIA GPU/CUDA recommended
- CPU/Turbo profile for systems without NVIDIA graphics
- Microphone and local storage for Whisper models
- Models are downloaded when first required and then used locally
Trial and licensing model
One-off payment with no automatic renewal.
14-day local trial · one named user · up to two personal devices · no automatic renewal.
Launch prices through 31 December 2026
Pricing options
Before purchase: Purchase & Licence Terms · Refunds & Withdrawal · Privacy. Payment processing is handled by Paddle as Merchant of Record.
1 year
59 €
Time-limited one-off licence with no automatic renewal.
2 years
99 €
Longer usage period with no automatic renewal.
Perpetual
149 €
For the current major version line; updates and standard support included for 12 months.
Live payment integration prepared; public release is still pending.
Purchase buttons remain disabled until final approval. After a successful purchase, the customer portal, licence and protected installer download are provided for the relevant product entitlement.
Frequently asked questions
Important questions before trial and purchase.
Does the application require an NVIDIA graphics card?
No. An NVIDIA/CUDA profile is designed for high-performance desktop systems; a CPU/Turbo compatibility path is also available for systems without NVIDIA graphics.
Is audio sent to a cloud service?
Transcription is designed for local processing. Whisper models are downloaded when first required and are then stored locally.
Which applications can receive dictated text?
The global F9 workflow is designed for suitable input fields in applications including Word, Outlook, browsers and PowerPoint.
Next step
Live checkout, customer portal and licence fulfilment are prepared.
The purchase and licence chain is prepared for live operation. Exactly one controlled live smoke test will follow before public release.