Update readme

Author: rawandahmad698

README.md

@@ -35,26 +35,23 @@ Now, Recap is broken. But it is a project that I am always working on in my free
 
 ---
 
-> [!IMPORTANT]
-> Recap is not complete yet, it is broken, and not recommended for production usage.
-
 > [!TIP]
 > Recap is in an incomplete state and I suggest that it is not used for production and daily usage, but help in shaping it is greatly appreciated.
 
 # Recap
 
 Recap is an open-source, privacy-focused, macOS-native project to help you summarize your meetings. You could summarize audio of any app, not just meetings.
 
-## Tech Stack
+## Stack
 
 #### Linter
 Not using any linter right now, but I am planning to use SwiftLint/SwiftFormat in the future (PRs greatly welcomed).
 
 Built using native macOS technologies - no drivers or kernel extensions required.
 
-**Core Audio**: Native Core Audio taps, AVAudioEngine, driver-free system audio capture  
-**ML**: WhisperKit (local transcription), Ollama/OpenRouter (summarization)  
-**Platform**: Swift + SwiftUI, Apple Silicon optimized, sandboxed execution
+-  Native Core Audio taps, AVAudioEngine, driver-free system audio capture  
+-  WhisperKit (MLX) (local transcription), Ollama/OpenRouter (summarization)  
+-  Swift + SwiftUI
 
 ### Roadmap:
 
@@ -68,13 +65,14 @@ Working on the following features now:
 
 Right now, Recap is more of a POC of what I am trying to make. It records system audio (Core Audio Taps) + with an optional microphone recording (your audio) and feeds it to Whisper for transcription and then uses Ollama for summarizing.
 
-**LLM Provider Options:**
+**LLM Options:**
 - **Ollama** (recommended): Complete privacy - everything stays on your device
 - **OpenRouter**: Cloud-based option if you lack local compute capacity, but data leaves your device
 
 ## System Requirements
 
-### For Ollama (Local Processing)
+<details>
+  <summary>Ollama (Local Processing)</summary>
 
 | Component | Minimum | Recommended |
 |-----------|---------|-------------|
@@ -83,27 +81,27 @@ Right now, Recap is more of a POC of what I am trying to make. It records system
 | **RAM** | 16 GB | 32 GB or more |
 | **Storage** | 10 GB free space | 50 GB free space |
 
-### For OpenRouter (Cloud Processing)
-
+<details>
+    <summary>OpenRouter (Cloud Processing)</summary>
 | Component | Minimum | Recommended |
 |-----------|---------|-------------|
 | **macOS** | 15.0 or later | 15.0 or later |
 | **Processor** | Apple M1 | Apple M2 or newer |
 | **RAM** | 8 GB | 16 GB or more |
 | **Storage** | 2 GB free space | 5 GB free space |
+</details>
 
-> **Note**: Intel Macs are not supported. Apple Silicon required for WhisperKit transcription.
+> **Note**: Intel Macs are not supported. Use it at your own risk.
 
 ## How It Works
 
 ```text
-                                  DATA FLOW
                               ┌───────────────┐
                           ┌───┤ 1. App Start  │
                           │   └───────────────┘
                           ▼
                     ┌─────────────┐
-                    │2. App Select │
+                    │2.App Select │
                     └─────────────┘
                           │
                           ▼
@@ -156,7 +154,6 @@ Currently, Recap is only available through compilation from source. Pre-built re
 
 3. **Build in Xcode:**
 
-   * Select your development team in project settings
    * Build and run (⌘+R)
 
 > **Note**: Distribution via Mac App Store and direct download will be available in future releases once the app reaches production readiness.
@@ -165,23 +162,37 @@ Currently, Recap is only available through compilation from source. Pre-built re
 
 ### Required Environment Variables
 
-Before using Recap, you need to set up the following environment variables:
+Before using, you need to set up the following environment variables:
 
 * **`HF_TOKEN`** (Required): Hugging Face token for downloading Whisper models
 
   ```bash
   export HF_TOKEN="your_huggingface_token_here"
   ```
 
+Read [Hugging Face documentation](https://huggingface.co/docs/hub/security-tokens) to get a token!
+
 * **`OPENROUTER_API_KEY`** (Optional): Only required if using OpenRouter for summarization
 
   ```bash
   export OPENROUTER_API_KEY="your_openrouter_api_key_here"
   ```
 
+Read [OpenRouter documentation](https://openrouter.ai/docs/api-keys) to get a key!
+
 ### First-Time Setup
 
-1. **Download Whisper Model:**
+#### Ollama Setup
+1. Download Ollama here: [Ollama](https://ollama.com/download)
+2. Pull the latest models (i.e. Llama 3):
+
+   ```bash
+   ollama pull llama3
+   ```
+
+#### Whisper Models
+
+1. **Download & Select a Model:**
 
    * Open Recap and go to **Settings → Whisper Models**
    * Download a Whisper model (recommended: **Large v3** for best accuracy)
@@ -200,42 +211,6 @@ Before using Recap, you need to set up the following environment variables:
    * Optionally enable microphone for dual-audio recording
    * Click stop when finished - processing will begin automatically
 
-## Tech Stack
-
-Recap is built using native macOS technologies, avoiding third-party drivers and kernel extensions for maximum system stability and security.
-
-### Core Audio Implementation
-
-* **Native Core Audio**: Direct integration with macOS audio subsystem
-* **Audio Unit Taps**: System-level audio interception without drivers
-* **AVAudioEngine**: Modern Swift audio processing pipeline
-* **No Kernel Extensions**: Driver-free audio capture using Apple's official APIs
-* **Process-Specific Capture**: Target individual applications without affecting system audio
-
-### Technologies Used
-
-* **Language**: Swift 5.9+
-* **UI Framework**: SwiftUI + AppKit (menu bar integration)
-* **Audio Processing**: Core Audio, AVAudioEngine, Audio Toolbox
-* **Machine Learning**:
-
-  * WhisperKit (local speech-to-text)
-  * MLX/CoreML optimization for Apple Silicon
-* **LLM Integration**:
-
-  * Ollama (local inference)
-  * OpenRouter (cloud API)
-* **Data Storage**: Core Data + local file system
-* **Concurrency**: Swift async/await, structured concurrency
-* **Architecture**: MVVM, Coordinator pattern, Dependency injection
-
-### Security & Privacy Benefits
-
-* **Sandboxed Execution**: Runs within macOS security boundaries
-* **No System Modifications**: Zero kernel-level changes required
-* **Permission-Based**: Uses standard macOS audio permissions
-* **Local Processing**: WhisperKit keeps transcription on-device
-* **Secure Audio Taps**: Apple's blessed method for audio interception
 
 ## Contributing
 
@@ -247,14 +222,6 @@ I really need help finishing Recap! Any contribution is greatly welcomed.
 
 * See Roadmap above for current focus areas
 
-**Also needed:**
-
-* Meeting app detection improvements
-* Custom prompt templates via settings
-* Performance optimizations
-* Documentation improvements
-* Bug fixes and stability improvements
-
 ### How to Contribute
 
 1. **Fork the repository** and create a feature branch
@@ -278,7 +245,7 @@ is prohibited without express prior written consent from the copyright holder.
 
 **What this means:**
 
-* ✅ **Any kind of usage allowed** — personal, educational, or commercial use and modification is permitted.
-* ❌ **Redistribution prohibited** — you may not redistribute the original or modified project in any form.
+* [x] **Any kind of usage allowed** — personal, educational, or commercial use and modification is permitted.
+* [ ] **Redistribution prohibited** — you may not redistribute the original or modified project in any form.
 
 Please see the [LICENSE](LICENSE) file for full details.