diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
new file mode 100644
index 0000000..432bc18
--- /dev/null
+++ b/.github/workflows/build.yml
@@ -0,0 +1,30 @@
+name: Build and Test
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    
+    permissions:
+      contents: read
+
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Setup Node.js
+      uses: actions/setup-node@v4
+      with:
+        node-version: '20'
+        cache: 'npm'
+    
+    - name: Install dependencies
+      run: npm ci
+    
+    - name: Build
+      run: npm run build
diff --git a/.github/workflows/jekyll-docker.yml b/.github/workflows/jekyll-docker.yml
deleted file mode 100644
index 3d0eedb..0000000
--- a/.github/workflows/jekyll-docker.yml
+++ /dev/null
@@ -1,20 +0,0 @@
-name: Jekyll site CI
-
-on:
-  push:
-    branches: [ "main" ]
-  pull_request:
-    branches: [ "main" ]
-
-jobs:
-  build:
-
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v4
-    - name: Build the site in the jekyll/builder container
-      run: |
-        docker run \
-        -v ${{ github.workspace }}:/srv/jekyll -v ${{ github.workspace }}/_site:/srv/jekyll/_site \
-        jekyll/builder:latest /bin/bash -c "chmod -R 777 /srv/jekyll && jekyll build --future"
diff --git a/broadcast-ai/README.md b/broadcast-ai/README.md
new file mode 100644
index 0000000..f5f4c80
--- /dev/null
+++ b/broadcast-ai/README.md
@@ -0,0 +1,149 @@
+# Palestinian AI Voice Broadcasting Platform
+
+## What This Does
+
+This platform creates authentic Arabic speech for broadcasting, trained specifically on Palestinian dialect and Quranic pronunciation patterns. It combines multiple voice datasets to produce natural-sounding news announcements and can generate synchronized video content.
+
+## Getting Started
+
+**Hardware needed:**
+- Computer with Python 3.8 or newer
+- At least 8 GB memory (more is better for model training)
+- Optional: NVIDIA GPU makes training much faster
+
+**Installation steps:**
+
+Execute the setup automation:
+```bash
+./setup.sh
+```
+
+The script handles ffmpeg installation and Python package configuration automatically.
+
+## How To Use This System
+
+### Step 1: Collect Voice Data
+
+Your audio samples go into six specialized folders. Each needs a `metadata.csv` file mapping audio filenames to their Arabic transcriptions using pipe delimiter format: `audiofile.wav|النص العربي`
+
+Reference the `.csv.example` files in each folder to see the expected format.
+
+**The six dataset categories:**
+- `dataset_quran` → Quranic verses with proper tajweed
+- `dataset_speaker` → General broadcaster voice samples  
+- `dataset_speaker_news` → Formal news presentation style
+- `dataset_speaker_palestinian` → Authentic Palestinian colloquial speech
+- `dataset_speaker_realistic` → Natural conversational patterns
+- `dataset_authority` → Official statement delivery style
+
+### Step 2: Build Your Model
+
+Run the training process:
+```bash
+python train.py
+```
+
+The trainer consolidates all your datasets and adapts the XTTS v2 foundation model. Output goes to `models/final_broadcast_model/`. Expect this to take time - possibly hours based on your dataset size and hardware.
+
+### Step 3: Create Audio Content
+
+Generate test audio:
+```bash
+python generate.py
+```
+
+The system produces `output/demo.wav` with professional audio treatment including frequency filtering and broadcast loudness standards (EBU R128 at -16 LUFS target).
+
+### Step 4: Launch Broadcasting (Optional)
+
+To enable video with lip synchronization, you need the Wav2Lip tool installed and an anchor presenter image at `input/anchor.jpg`.
+
+Start the broadcast generator:
+```bash
+python run_tv_channel.py &
+```
+
+Start the web interface:
+```bash
+python tv_server.py
+```
+
+View output at localhost port 3000.
+
+## Programming Interface
+
+Import the voice generation function:
+
+```python
+from generate import generate_voice
+
+generated_file = generate_voice(
+    text="نص عربي هنا",
+    style="news",
+    output_name="output_filename.wav"
+)
+```
+
+The function returns the path to your generated audio file.
+
+## File Organization
+
+- `train.py` → Dataset merging and model fine-tuning
+- `generate.py` → Speech synthesis with audio processing  
+- `run_tv_channel.py` → Automated segment generation loop
+- `tv_server.py` → HTTP streaming endpoint (Flask-based)
+- `requirements.txt` → Python dependencies list
+- `setup.sh` → Automated environment configuration
+
+Generated content appears in `output/`, trained models in `models/`, source recordings in `dataset_*/wavs/`.
+
+## Audio Quality Tips
+
+**Recording standards:**
+- Sample at 16000 Hz minimum
+- Remove background noise before use
+- Normalize volume across all samples
+- Use consistent microphone setup
+
+**Dataset composition:**
+- Target 100+ recordings per category for good results
+- Balance formal and informal speaking styles
+- Mix different sentence structures and lengths
+- Include Arabic diacritics for Quran dataset accuracy
+
+## Configuration Changes
+
+**Switch reference voice:**
+Modify `REFERENCE_WAV` path in `generate.py` to point at your preferred sample.
+
+**Adjust audio filters:**
+Edit the `af_chain` variable in `generate.py` to customize frequency response and loudness targets.
+
+**Update news content:**
+Modify `NEWS_HEADLINES` array in `run_tv_channel.py` to change broadcast content pool.
+
+## Common Issues
+
+**Training fails with memory error:**
+Your system needs more RAM or reduce the batch size parameter.
+
+**Cannot find model:**
+Complete the training step first before attempting generation.
+
+**Video generation skips lip sync:**
+Verify Wav2Lip installation and checkpoint file presence at `models/wav2lip.pth`.
+
+**FFmpeg command not found:**
+Install via your package manager (apt, brew, yum) or download from official site.
+
+## Web Server Endpoints
+
+- Root `/` serves the Arabic RTL player interface
+- `/stream` provides direct media access  
+- `/health` returns JSON status for monitoring
+
+## Technical Notes
+
+The system merges diverse Arabic speech patterns to capture authentic Palestinian broadcasting style while maintaining clear pronunciation through Quranic conditioning. Audio post-processing applies industry-standard loudness normalization suitable for broadcast transmission.
+
+Model training adapts the multilingual XTTS v2 architecture with your custom Arabic datasets. The generator uses your reference voice sample to guide prosody and timbre during synthesis.
diff --git a/broadcast-ai/generate.py b/broadcast-ai/generate.py
index 8ecbfb8..6f4e475 100644
--- a/broadcast-ai/generate.py
+++ b/broadcast-ai/generate.py
@@ -85,16 +85,23 @@ def generate_voice(
         "loudnorm=I=-16:LRA=11:TP=-1.5"
     )
 
-    subprocess.run(
-        [
-            "ffmpeg", "-y",
-            "-i", raw_path,
-            "-af", af_chain,
-            final_path,
-        ],
-        check=True,
-        capture_output=True,
-    )
+    try:
+        subprocess.run(
+            [
+                "ffmpeg", "-y",
+                "-i", raw_path,
+                "-af", af_chain,
+                final_path,
+            ],
+            check=True,
+            capture_output=True,
+        )
+    except (subprocess.CalledProcessError, FileNotFoundError) as e:
+        error_type = "not found" if isinstance(e, FileNotFoundError) else "failed"
+        print(f"[WARN] ffmpeg {error_type} - skipping audio post-processing")
+        print(f"[WARN] Using raw audio output instead")
+        # If ffmpeg fails or is not installed, use the raw audio file
+        final_path = raw_path
 
     print(f"[GEN] {style} → {final_path}")
     return final_path
diff --git a/broadcast-ai/run_tv_channel.py b/broadcast-ai/run_tv_channel.py
index 082f5dd..82627ed 100644
--- a/broadcast-ai/run_tv_channel.py
+++ b/broadcast-ai/run_tv_channel.py
@@ -56,20 +56,25 @@ def _ensure_anchor_video():
         return
 
     os.makedirs("input", exist_ok=True)
-    subprocess.run(
-        [
-            "ffmpeg", "-y",
-            "-loop", "1",
-            "-i", anchor_img,
-            "-c:v", "libx264",
-            "-t", "15",
-            "-pix_fmt", "yuv420p",
-            ANCHOR_VIDEO,
-        ],
-        check=True,
-        capture_output=True,
-    )
-    print(f"[ANCHOR] Created {ANCHOR_VIDEO}")
+    try:
+        subprocess.run(
+            [
+                "ffmpeg", "-y",
+                "-loop", "1",
+                "-i", anchor_img,
+                "-c:v", "libx264",
+                "-t", "15",
+                "-pix_fmt", "yuv420p",
+                ANCHOR_VIDEO,
+            ],
+            check=True,
+            capture_output=True,
+        )
+        print(f"[ANCHOR] Created {ANCHOR_VIDEO}")
+    except subprocess.CalledProcessError as e:
+        print(f"[ERROR] Failed to create anchor video: {e}")
+    except FileNotFoundError:
+        print(f"[ERROR] ffmpeg not found - cannot create anchor video")
 
 
 def _generate_segment(headline: str) -> str | None:
@@ -85,18 +90,26 @@ def _generate_segment(headline: str) -> str | None:
         print("[WARN] Wav2Lip checkpoint not found — skipping lip-sync")
         return audio_path
 
-    subprocess.run(
-        [
-            "python", WAV2LIP_INFERENCE,
-            "--checkpoint_path", WAV2LIP_CHECKPOINT,
-            "--face", ANCHOR_VIDEO,
-            "--audio", audio_path,
-            "--outfile", VIDEO_OUTPUT,
-        ],
-        check=True,
-    )
-
-    return VIDEO_OUTPUT
+    try:
+        subprocess.run(
+            [
+                "python", WAV2LIP_INFERENCE,
+                "--checkpoint_path", WAV2LIP_CHECKPOINT,
+                "--face", ANCHOR_VIDEO,
+                "--audio", audio_path,
+                "--outfile", VIDEO_OUTPUT,
+            ],
+            check=True,
+        )
+        return VIDEO_OUTPUT
+    except subprocess.CalledProcessError as e:
+        print(f"[WARN] Wav2Lip processing failed: {e}")
+        print(f"[WARN] Falling back to audio only")
+        return audio_path
+    except FileNotFoundError:
+        print(f"[WARN] Python interpreter or Wav2Lip script not found")
+        print(f"[WARN] Falling back to audio only")
+        return audio_path
 
 
 # ---------------------------------------------------------------------------
@@ -119,8 +132,12 @@ def run():
             result = _generate_segment(headline)
             if result:
                 print(f"[TV] Segment ready: {result}")
+        except KeyboardInterrupt:
+            print("[TV] Shutting down broadcast loop")
+            break
         except Exception as exc:
-            print(f"[TV] Segment failed: {exc}")
+            print(f"[TV] Unexpected error during segment generation ({type(exc).__name__}): {exc}")
+            print("[TV] Continuing to next segment...")
 
         time.sleep(LOOP_PAUSE_SECONDS)
 
diff --git a/broadcast-ai/setup.sh b/broadcast-ai/setup.sh
index d7fd0f5..e7ae96b 100755
--- a/broadcast-ai/setup.sh
+++ b/broadcast-ai/setup.sh
@@ -8,23 +8,45 @@ echo "============================================"
 echo " Palestinian AI Broadcast — Setup"
 echo "============================================"
 
+# --- Python version check ----------------------------------------------------
+echo "[1/5] Checking Python version..."
+if ! command -v python3 &>/dev/null; then
+    echo "[ERROR] Python 3 is required but not found"
+    exit 1
+fi
+PYTHON_VERSION=$(python3 --version 2>&1 | awk '{print $2}' | cut -d'.' -f1,2)
+echo "✓ Python $PYTHON_VERSION detected"
+
 # --- System dependencies ----------------------------------------------------
-echo "[1/3] Installing system packages..."
+echo "[2/5] Installing system packages..."
 if command -v apt-get &>/dev/null; then
     sudo apt-get update -qq
     sudo apt-get install -y -qq ffmpeg
+    echo "✓ ffmpeg installed via apt-get"
 elif command -v yum &>/dev/null; then
     sudo yum install -y ffmpeg
+    echo "✓ ffmpeg installed via yum"
+elif command -v brew &>/dev/null; then
+    brew install ffmpeg
+    echo "✓ ffmpeg installed via brew"
 else
     echo "[WARN] Cannot detect package manager. Install ffmpeg manually."
 fi
 
+# Verify ffmpeg installation
+if command -v ffmpeg &>/dev/null; then
+    echo "✓ ffmpeg verified: $(ffmpeg -version | head -n1)"
+else
+    echo "[WARN] ffmpeg not found in PATH. Some features may not work."
+fi
+
 # --- Python dependencies ----------------------------------------------------
-echo "[2/3] Installing Python dependencies..."
-pip install -q -r requirements.txt
+echo "[3/5] Installing Python dependencies..."
+pip3 install -q -r requirements.txt
+echo "✓ Python packages installed"
 
 # --- Directory structure -----------------------------------------------------
-echo "[3/3] Verifying directory structure..."
+echo "[4/5] Creating directory structure..."
 dirs=(
     dataset_quran/wavs
     dataset_speaker/wavs
@@ -40,17 +62,30 @@ dirs=(
 for d in "${dirs[@]}"; do
     mkdir -p "$d"
 done
+echo "✓ Directory structure ready"
+
+# --- Create example CSV files -----------------------------------------------
+echo "[5/5] Creating example metadata files..."
+for dataset in dataset_quran dataset_speaker dataset_speaker_news dataset_speaker_palestinian dataset_speaker_realistic dataset_authority; do
+    if [ ! -f "$dataset/metadata.csv.example" ]; then
+        cat > "$dataset/metadata.csv.example" << 'EOF'
+audio_001.wav|النص العربي هنا
+audio_002.wav|مثال آخر للنص العربي
+EOF
+        echo "✓ Created $dataset/metadata.csv.example"
+    fi
+done
 
 echo ""
 echo "============================================"
-echo " Setup complete!"
+echo " ✓ Setup complete!"
 echo "============================================"
 echo ""
 echo "Next steps:"
 echo "  1. Add WAV files and metadata.csv to each dataset_* directory"
 echo "     (see *.csv.example files for the format)"
 echo "  2. Place an anchor image at input/anchor.jpg"
-echo "  3. Run:  python train.py"
-echo "  4. Run:  python run_tv_channel.py   (Terminal 1)"
-echo "  5. Run:  python tv_server.py         (Terminal 2)"
+echo "  3. Run:  python3 train.py"
+echo "  4. Run:  python3 run_tv_channel.py   (Terminal 1)"
+echo "  5. Run:  python3 tv_server.py         (Terminal 2)"
 echo ""
diff --git a/qudscast-ai/setup.sh b/qudscast-ai/setup.sh
index 4934d0b..656c253 100644
--- a/qudscast-ai/setup.sh
+++ b/qudscast-ai/setup.sh
@@ -1,34 +1,63 @@
 #!/bin/bash
 # QudsCast AI - Setup Script
+set -e
 
 echo "========================================"
 echo "  QudsCast AI - Setup"
 echo "========================================"
 
-# Install backend dependencies
-echo "Installing backend dependencies..."
-npm install
+# Check Node.js version
+echo "[1/7] Checking Node.js version..."
+NODE_VERSION=$(node --version | cut -d'v' -f2 | cut -d'.' -f1)
+if [ "$NODE_VERSION" -lt 18 ]; then
+    echo "ERROR: Node.js 18+ is required (found: $(node --version))"
+    exit 1
+fi
+echo "✓ Node.js $(node --version) detected"
 
-# Install frontend dependencies
-echo "Installing frontend dependencies..."
-cd frontend && npm install && cd ..
+# Setup environment file
+echo "[2/7] Setting up environment configuration..."
+if [ ! -f .env ]; then
+    cp .env.example .env
+    echo "✓ Created .env from .env.example"
+else
+    echo "✓ .env already exists"
+fi
+
+# Create storage directories
+echo "[3/7] Creating storage directories..."
+mkdir -p storage/voices storage/jingles storage/audio storage/videos
+echo "✓ Storage directories ready"
+
+# Install all dependencies
+echo "[4/7] Installing dependencies..."
+npm run install:all
 
 # Build frontend
-echo "Building frontend..."
+echo "[5/7] Building frontend..."
 cd frontend && npm run build && cd ..
+echo "✓ Frontend build complete"
 
 # Install Python dependencies (optional)
-echo "Installing Python TTS dependencies..."
-pip install gtts 2>/dev/null || pip3 install gtts 2>/dev/null || echo "Python TTS installation skipped"
+echo "[6/7] Installing Python TTS dependencies..."
+if command -v pip3 &>/dev/null; then
+    pip3 install gtts 2>/dev/null && echo "✓ Python TTS installed" || echo "⚠ Python TTS installation skipped"
+elif command -v pip &>/dev/null; then
+    pip install gtts 2>/dev/null && echo "✓ Python TTS installed" || echo "⚠ Python TTS installation skipped"
+else
+    echo "⚠ pip not found - Python TTS installation skipped"
+fi
 
 # Make scripts executable
+echo "[7/7] Setting script permissions..."
 chmod +x backend/audio/generate_radio_mp3.sh
 chmod +x backend/video/generate_video.sh
 chmod +x backend/tts/generate_voice.py
+echo "✓ Scripts are executable"
 
 echo ""
 echo "========================================"
-echo "  Setup Complete!"
+echo "  ✓ Setup Complete!"
 echo "========================================"
 echo ""
 echo "To start the application:"