Update app.py

app.py

@@ -29,6 +29,12 @@ SUPPORTED_TTS_LANGUAGES = {
     "pt": "p",  # Brazilian Portuguese
 }
 
+# Available voices in KokoroTTS
+AVAILABLE_VOICES = [
+    'af_bella', 'af_sarah', 'am_adam', 'am_michael', 'bf_emma',
+    'bf_isabella', 'bm_george', 'bm_lewis', 'af_nicole', 'af_sky'
+]
+
 ### 1️⃣ Fetch and Extract Content (Runs Immediately)
 def fetch_and_display_content(url):
     """Fetch and extract text from a given URL (HTML or PDF)."""
@@ -40,7 +46,11 @@ def fetch_and_display_content(url):
         text = extract(downloaded, output_format="markdown", with_metadata=True, include_tables=False, include_links=False, include_formatting=True, include_comments=False) #without metadata extraction
     metadata, cleaned_text = extract_and_clean_text(text)
     detected_lang = detect_language(cleaned_text)
-    return cleaned_text, detected_lang, gr.update(visible=True), gr.update(visible=True)
+
+    # Add detected language to metadata
+    metadata["Detected Language"] = detected_lang.upper()
+    #return cleaned_text, detected_lang, gr.update(visible=True), gr.update(visible=True)
+    return cleaned_text, metadata, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)
 
 ### 2️⃣ Cleaning Function
 def extract_and_clean_text(data):
@@ -92,9 +102,10 @@ def extract_and_clean_text(data):
         
         return text
 
-    cleaned_text = clean_text(data)
+    #cleaned_text = clean_text(data)
 
-    return metadata_dict, cleaned_text
+    #return metadata_dict, cleaned_text
+    return metadata_dict, clean_text(data)
 
 ### 3️⃣ Language Detection
 def detect_language(text):
@@ -111,7 +122,8 @@ def generate_audio_kokoro(text, lang):
     """Generate speech using KokoroTTS for supported languages."""
     global kokoro_tts  # Access the preloaded model
     lang_code = SUPPORTED_TTS_LANGUAGES.get(lang, "a")  # Default to English
-    generator = kokoro_tts(text, voice="af_bella", speed=1, split_pattern=r'\n+')
+    #generator = kokoro_tts(text, voice="af_bella", speed=1, split_pattern=r'\n+')
+    generator = kokoro_tts(text, voice=selected_voice, speed=1, split_pattern=r'\n+')
 
     # Generate and collect audio data
     audio_data_list = [audio for _, _, audio in generator]
@@ -149,24 +161,35 @@ with gr.Blocks() as demo:
     url_input = gr.Textbox(label="Enter URL", placeholder="https://example.com/article")
     #process_button = gr.Button("Generate Audio")
 
+    voice_selection = gr.Dropdown(AVAILABLE_VOICES, label="Select Voice", value="af_bella")
+
     process_text_button = gr.Button("Fetch Text & Detect Language")
     process_audio_button = gr.Button("Generate Audio", visible=False)
+
+    # Layout: Two adjacent columns (Text and Metadata)
+    with gr.Row():
+        extracted_text = gr.Textbox(label="Extracted Content", visible=False, interactive=False, lines=15)
+        metadata_output = gr.JSON(label="Article Metadata", visible=False)  # Displays metadata
+
     
-    extracted_text = gr.Markdown(label="Extracted Content")
-    detected_language = gr.Textbox(label="Detected Language")
-    full_audio_output = gr.Audio(label="Generated Audio")
+    #extracted_text = gr.Markdown(label="Extracted Content")
+    #detected_language = gr.Textbox(label="Detected Language")
+    #full_audio_output = gr.Audio(label="Generated Audio")
+    full_audio_output = gr.Audio(label="Generated Audio", visible=False)
 
     # Step 1: Fetch Text & Detect Language First
     process_text_button.click(
         fetch_and_display_content, 
         inputs=[url_input], 
-        outputs=[extracted_text, detected_language, process_audio_button, extracted_text]
+        #outputs=[extracted_text, detected_language, process_audio_button, extracted_text]
+        outputs=[extracted_text, metadata_output, process_audio_button, extracted_text, metadata_output]
     )
-
+    
     # Step 2: Generate Audio After Text & Language Are Displayed
     process_audio_button.click(
         generate_audio_kokoro, 
-        inputs=[extracted_text, detected_language], 
+        #inputs=[extracted_text, detected_language], 
+        inputs=[extracted_text, metadata_output, voice_selection],
         outputs=[full_audio_output]
     )