dIKta.me User Guide
Three Inputs. Infinite Output.
dIKta.me reads the world through three inputs — and turns any of them into whatever you need.
| Input | What it captures | Start here |
|---|---|---|
| 🎤 Voice | Your microphone, via a global hotkey | Voice |
| 📝 Text Selection | Any highlighted text in any app | Text Selection |
| 🖥️ Screen | Windows, regions, full monitors, or colors | Screen |
Each input can flow into any of the outputs below. Mix and match: voice into Dictate for formatted typing, text selection into Refine for a cleanup, screen into Vision for OCR, voice + screen into a Quick Chat for multimodal reasoning.
Outputs
- Dictate — voice becomes formatted text at your cursor
- Refine — clean up or rewrite highlighted text
- Ask — a direct line to your AI for quick questions
- Translate — speak one language, get another
- Note — capture thoughts to a file without losing focus
- Vision Actions — OCR, describe, tables, color picker, video capture
- Quick Chat — a floating assistant for multi-turn conversations
- Oops — undo or re-inject the last response
- Voice Macros — magic phrases that expand into full text
- Text-to-Speech — let the app read text aloud
Start here
- Getting Started — installed in 2 minutes flat
- Troubleshooting — if something feels off, look here first
- Settings — make it yours
Stuck? Check out our GitHub Issues to see if others have found a solution.