STOP TYPING.STARTTALKING.THINKING.WORKING.WINNING.
The only open-source, local-first voice engine for Windows.
Your ideas never leave your sight!
-- "Work at the speed of your thoughts, not the speed of your fingers" --
The Core Arsenal.
Four modes. Infinite productivity. Zero latency.
Dictate
The Input. 1,000 WPM local transcription with RAW Mode for instant, unfiltered injection into any application.
Ask
The Brain. Query your local LLM instantly for definitions, math, or quick facts without ever leaving your active window.
Refine
The Finish. Professional-grade AI editing. Transform rough transcripts into polished emails or documentation instantly.
Structured Notes
The Memory. Capture thoughts with automatic timestamps and metatags. Sequential formatting ready for batch processing.
dIKta.me Versus The Cloud.
Why settle for rental when you can own the factory?
| Feature | The Others | dIKta.me |
|---|---|---|
| Privacy | Sent to servers | 100% Local (Air-Gapped) |
| Speed | 800-1200ms Latency/Inference | ~400ms (Local GPU Inference - gemma3:1b *) |
| Consistency | Varies by Web Traffic | Hardware-Bound (Stable) |
| Censorship | Aggressive Filtering | Zero Restrictions |
| Cost | $240 / year | $10 - $25 (Once) |
| Word Limits | Capped | Unlimited while on Local |
| Offline Use | Requires WiFi | Works in a Bunker |
The Specs.
Everything you need to make your voice heard. Nothing you don't.
Whisper V3 Turbo
State-of-the-art accuracy running locally. Use it in RAW Mode for instant transcription and injection with good tolerance for filler and punctuation correction.
Local Small Model Brain
Intelligent formatting, filler removal, excellent math, and general knowledge. Utilize different models for various simple tasks, all local, all private, and all exceptionally fast.
Global Configurable Hotkeys
Ctrl+Alt+D (Dictate)
Ctrl+Alt+A (Ask)
Ctrl+Alt+R (Refine Auto & Freeform)
Ctrl+Alt+T (Translate)
Ctrl+Alt+V (Re-inject Last)
Precision Injection
Zero-latency, 1,000 WPM text injection with native window emulation across every application.
Intelligent Modes
Standard - Direct Injection
Professional - Polished Output
Prompt - AI Instruction mode
Raw - Unfiltered Stream
Hybrid Cloud Bridge
Seamlessly transition from local execution to Gemini 2.0 via one-click Google OAuth.
API Freedom
No markup, no middleman. Plug in your own OpenAI, Anthropic, or DeepSeek keys directly.
Cross-Lingual Engine
Real-time ES ↔ EN translation integrated at the model level for zero-latency bridging.
Local Privacy Guard
100% local processing with automatic PII and sensitive data scrubbing from all logs.
Encrypted SafeStorage
Secrets and keys are managed via OS-level AES-256 encryption. Never exposed, never raw.
Floating Pill
Unobtrusive overlay. Out of your way.
Self-Contained Binary
Single 150MB portable .exe includes a full Python runtime and embedded Ollama engine.
Voice Macros (Coming v2.0)
Expand snippets and signatures instantly.
Model Agnostic
Switch between Llama, Mistral, or Gemma.
Smart Fallback
Intelligent session recovery—never lose a word of dictation if a model hangs or crashes.
Hackable Core
Built on ZeroMQ. Exposes a plugin stream.
We Speak Spanish.
Hablamos Inglés.
Real-time translation at the edge. Dictate freely in your native tongue and let the engine bridge the gap instantly.
- ✓ No API keys required
- ✓ English → Spanish supported
- ✓ Context-aware translation
Don't Search.
Just Ask.
Skip the browser tab. Query your local LLM instantly for definitions, math, or quick facts without ever leaving your flow.
- ✓ Instant Q&A - Math, quotes, refs
- ✓ No Tracking - Local execution
- ✓ Zero Context Switch - Stay in flow
Your Tokens.
Your Choice.
Use local, use API Keys, its your choice, not theirs. Anthropic, Google, Deepseek, or local Ollama — dIKta.me unifies them all.
- ✓ BYO Keys - No markup, ever.
- ✓ Local First - Ollama & Llama.cpp
- ✓ Infinite Flexibility - Switch in seconds
- TERMINAL
- CURSOR
- ANTIGRAVITY
- GOOGLE DOCS
- NOTEPAD
- VS CODE
- SLACK
- EXCEL
- DISCORD
- OUTLOOK
- CHROME
- ARC
Stop Renting Software.
No monthly fees. No word limits. Just great tools you own.
Full App Trial
Test the cloud engine with Wallet credits.
- ✓ Minimum friction, high control
- ✓ Deepgram STT & Gemini Flash LLM
- ✓ Instant Access to Core Modes
- ✓ Unlimited Custom Presets
- ✓ Quick Chat Access included
- ✕ No Offline AI (Cloud Only)
Pre-loaded wallet included.
Power Version
The complete arsenal.
- ✓ Unrestricted Full App access
- ✓ Ask Mode UI
- ✓ Bilingual Bridge (ES ↔ EN)
- ✓ Context Modes & Macros
- ✓ +Key (Auto-Enter/Tab)
- ✓ Source-Available License
One-time payment. Forever.
Build It Yourself
- 📚 Full Source Code
- 📖 In-Depth Build Guide