Update README.md

README.md

@@ -4,164 +4,200 @@ language:
   - sk
   - en
   - de
+
 license: apache-2.0
+
 base_model: EuroLLM-9B
+
 quantization: Q8_0
+
+pipeline_tag: text-generation
+
+library_name: llama.cpp
+
 tags:
   - gguf
   - llama.cpp
   - offline
+  - offline-first
   - local-ai
   - multilingual
-  - cli-runtime
   - ai-runtime
-pipeline_tag: text-generation
-library_name: llama.cpp
+  - webui
+  - cli
+  - voice
+  - speech-to-text
+  - text-to-speech
+  - privacy
 ---
 
-# Offline AI 2.2 – EuroLLM-9B-Q8_0 (GGUF)
+# Offline AI Runtime 3.0 – EuroLLM-9B-Q8_0 (GGUF)
 
-Offline AI 2.2 is a fully local AI runtime environment built around digital sovereignty, privacy, and system autonomy.
+Offline AI Runtime 3.0 is a fully local AI runtime environment focused on digital sovereignty, privacy, and user-controlled AI.
 
-No cloud.  
-No telemetry.  
-No tracking.  
-No external dependencies.  
-
-Everything runs locally via **llama.cpp**.
-
----
+Everything runs entirely on your own computer.
 
-## 🖥️ CLI Preview
+**No cloud.**  
+**No telemetry.**  
+**No tracking.**  
+**No subscriptions.**
 
-Below is the Offline AI runtime interface:
+Powered by **llama.cpp**.
 
-![Offline AI CLI Help Menu](cli_help_menu.png)
+---
 
-Offline AI is no longer just a model launcher.
+# 🖥️ Runtime Interfaces
 
-It is a **local AI runtime environment** designed to manage and operate language models fully offline with a structured command interface.
+Offline AI provides multiple ways to interact with local AI:
 
-Core capabilities include:
+- Terminal (CLI)
+- Modern Web UI
+- Voice interaction (Speech-to-Text + Text-to-Speech)
 
-- CLI runtime environment  
-- Model lifecycle management  
-- Profile-based workspace system  
-- Snapshot conversation archiving  
-- Runtime diagnostics and monitoring  
-- Administrative control layer  
+All interfaces use the same local runtime and the same locally running language models.
 
-The architecture is designed as a foundation for **multi-model local AI systems**.
+![Terminal or Web UI](Terminal_WebUI.png)
 
 ---
 
-## 🧠 RUNTIME ARCHITECTURE
+# ✨ What's New in 3.0
 
-Offline AI uses a layered architecture:
+Offline AI has evolved from a simple model launcher into a complete local AI runtime platform.
 
-User (CLI)
-↓
-Python Runtime
-↓
-C++ Inference Engine (llama.cpp)
-↓
-GGUF Language Model
+New features include:
 
+- Modern Web UI
+- Structured CLI runtime
+- Voice conversations (STT + TTS)
+- Runtime model switching
+- Model lifecycle management
+- Model alias system
+- Workspace profiles
+- Conversation snapshots
+- Notes system
+- Runtime diagnostics
+- Administrative control mode
+- Improved modular architecture
 
-The Python runtime acts as the **control layer**, responsible for:
+Designed for running multiple local AI models inside a unified offline environment.
 
-- command handling  
-- model orchestration  
-- workspace profiles  
-- snapshots and notes  
-- system diagnostics  
-- administrative operations  
+---
 
-The inference backend is a lightweight C++ wrapper around **llama.cpp** with real-time token streaming.
+# 🧠 Runtime Architecture
+
+```text
+CLI / Web UI / Voice
+          │
+          ▼
+ Offline AI Runtime
+          │
+ ├── Profiles
+ ├── Notes
+ ├── Snapshots
+ ├── Diagnostics
+ ├── Voice
+ ├── Model Manager
+ └── Runtime Commands
+          │
+          ▼
+      llama.cpp
+          │
+          ▼
+     GGUF Models
+```
+
+The Python runtime acts as the orchestration layer while **llama.cpp** provides efficient local inference with real-time token streaming.
 
 ---
 
-## 🔧 TECHNICAL INFORMATION
+# 🔧 Technical Information
 
-Base model: EuroLLM-9B  
-Quantization: Q8_0 (GGUF)  
-Format: llama.cpp compatible  
-Inference engine: llama.cpp  
-Offline AI Version: 2.2  
-Recommended RAM: 16 GB  
-Platforms: macOS, Windows, Linux  
+| Component | Value |
+|-----------|-------|
+| Base model | EuroLLM-9B |
+| Quantization | Q8_0 |
+| Format | GGUF |
+| Runtime | Offline AI Runtime 3.0 |
+| Inference Engine | llama.cpp |
+| Recommended RAM | 16 GB |
+| Platforms | macOS • Windows • Linux |
 
-This repository distributes a **quantized GGUF Q8_0 variant** of the EuroLLM-9B model optimized for efficient local inference.
+This repository distributes an **unmodified quantized GGUF version** of EuroLLM-9B.
 
-The original model weights are **not modified and not fine-tuned** as part of this project.
+The original model has **not been fine-tuned or modified** as part of this project.
 
 ---
 
-## 🚀 WHAT'S NEW IN 2.2
+# 🔐 Project Philosophy
 
-- Structured CLI runtime environment  
-- Model lifecycle management system  
-- Model alias system  
-- Workspace profiles and isolation  
-- Snapshot conversation archiving  
-- Runtime diagnostics and monitoring  
-- Administrative control mode  
-- Improved modular runtime architecture  
+Offline AI explores a different direction for modern AI.
 
-Offline AI 2.2 evolves the project from a simple model launcher into a **local AI runtime platform** prepared for managing multiple specialized AI models.
+The project demonstrates that:
+
+- AI can work without cloud services.
+- AI belongs to its owner.
+- Privacy should be the default.
+- Users should control their own models.
+- Local-first AI is a viable architecture.
+
+Offline AI promotes:
+
+- Digital sovereignty
+- Local-first computing
+- Transparent system design
+- Open AI ecosystems
+- Privacy by default
 
 ---
 
-## 🔐 PROJECT PHILOSOPHY
+# 📄 Model Origin & License
 
-Offline AI demonstrates that modern AI systems can operate fully offline.
+**Base Model**
 
-The project explores the idea that:
+EuroLLM-9B
 
-- AI does not require cloud infrastructure  
-- Open models can run independently on personal hardware  
-- AI tools can respect user privacy  
-- Local-first computing is a viable architecture  
+**Authors**
 
-Offline AI promotes:
+EuroLLM Consortium
 
-- Digital sovereignty  
-- Transparent system design  
-- Offline experimentation  
-- User-controlled AI environments  
+**Base Model License**
 
----
+Apache License 2.0
+
+**Runtime Engine**
 
-## 📄 MODEL ORIGIN & LICENSE
+llama.cpp (MIT License)
 
-Model: EuroLLM-9B  
-Original authors: EuroLLM Project consortium  
-Funded by: European Union research initiatives  
-Base model license: Apache License 2.0  
+**Offline AI Runtime**
 
-Quantized distribution: GGUF Q8_0  
-Runtime engine: llama.cpp (MIT License)  
-Offline AI runtime interface: © David Káninský  
+© David Káninský
 
-All components are used in compliance with their respective licenses.
+All components are distributed in accordance with their respective licenses.
 
 ---
 
-## ⚠️ DISCLAIMER
+# ⚠️ Disclaimer
 
-This project is an educational and experimental implementation.
+Offline AI is an educational and experimental runtime environment.
 
-It is not a commercial AI service and does not replace professional advice.  
-Outputs are not intended for legal, medical, financial, or critical decision-making use.
+Generated responses may contain inaccuracies and should not be used as the sole basis for legal, medical, financial, or other high-risk decisions.
 
-Use beyond personal, research, or educational purposes is at your own responsibility.
+Users are responsible for how the software and generated content are used.
 
 ---
 
-## 🌍 PROJECT
+# 🌍 Project
+
+**Website**
+
+https://OfflineAI.online
+
+Additional domains:
+
+- OfflineAI.cz
+- OfflineAI.sk
+- OfflineAI.de
 
-Website: https://OfflineAI.online  
-Domains: .cz / .sk / .de  
+**Author**
 
-Offline AI Runtime  
-Author: David Káninský
+David Káninský