Add ElevenLabs TTS for VIVA questions

app.py

@@ -13,11 +13,57 @@ load_dotenv()
 
 SERPAPI_KEY = os.getenv("SERPAPI_KEY")
 HYPERBOLIC_API_KEY = os.getenv("HYPERBOLIC_API_KEY")
+ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
 
 # Hyperbolic API configuration
 HYPERBOLIC_API_URL = "https://api.hyperbolic.xyz/v1/chat/completions"
 HYPERBOLIC_MODEL = "meta-llama/Llama-3.3-70B-Instruct"
 
+# ElevenLabs API configuration
+ELEVENLABS_API_URL = "https://api.elevenlabs.io/v1/text-to-speech"
+# Using a standard "Professor" like voice (e.g., "Brian" - a deep, authoritative British voice, or similar)
+# Voice ID for "Brian": nPczCjzI2devNBz1zQrb
+ELEVENLABS_VOICE_ID = "nPczCjzI2devNBz1zQrb" 
+
+def generate_audio(text: str) -> str:
+    """
+    Generate audio from text using ElevenLabs API.
+    Returns path to temporary audio file or None if failed.
+    """
+    if not ELEVENLABS_API_KEY or not text:
+        return None
+        
+    try:
+        url = f"{ELEVENLABS_API_URL}/{ELEVENLABS_VOICE_ID}"
+        headers = {
+            "Accept": "audio/mpeg",
+            "Content-Type": "application/json",
+            "xi-api-key": ELEVENLABS_API_KEY
+        }
+        data = {
+            "text": text,
+            "model_id": "eleven_monolingual_v1",
+            "voice_settings": {
+                "stability": 0.5,
+                "similarity_boost": 0.5
+            }
+        }
+        
+        response = requests.post(url, json=data, headers=headers)
+        
+        if response.status_code == 200:
+            # Save to temp file
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as f:
+                f.write(response.content)
+                return f.name
+        else:
+            print(f"ElevenLabs API Error: {response.text}")
+            return None
+            
+    except Exception as e:
+        print(f"Error generating audio: {str(e)}")
+        return None
+
 def is_anatomy_related(query: str) -> tuple[bool, str]:
     """
     Validate if the query is anatomy-related using the LLM.
@@ -516,6 +562,10 @@ def start_viva_mode(topic, image):
    
     # Start with question 1
     q1 = questions[0]
+    
+    # Generate audio for first question
+    audio_path = generate_audio(q1['question'])
+    
     return (
         gr.update(visible=True),  # Show VIVA container
         f"**VIVA MODE ACTIVE** 📝\nTopic: {topic}",  # viva_status
@@ -525,7 +575,8 @@ def start_viva_mode(topic, image):
         "",  # Clear answer input
         "",  # Clear feedback
         gr.update(interactive=True, value="Submit Answer"),  # Enable submit button
-        questions  # Store questions in state
+        questions,  # Store questions in state
+        audio_path  # Return audio path
     )
 
 
@@ -544,13 +595,18 @@ def submit_viva_answer(answer, questions, current_q_idx):
         next_q = questions[next_idx]
         next_question = f"### Question {next_idx + 1} of 5\n\n**{next_q['question']}**"
         next_hint = f"💡 **Hint:** {next_q.get('hint', 'Think carefully about the anatomical relationships.')}"
+        
+        # Generate audio for next question
+        audio_path = generate_audio(next_q['question'])
+        
         return (
             next_question,  # Show next question
             next_hint,  # Show next hint
             "",  # Clear answer box
             feedback_text,  # Show feedback for current answer
             gr.update(interactive=True, value="Submit Answer"),  # Keep button enabled
-            next_idx  # Update question index
+            next_idx,  # Update question index
+            audio_path  # Play next question audio
         )
     else:
         # VIVA complete
@@ -561,7 +617,8 @@ def submit_viva_answer(answer, questions, current_q_idx):
             "",  # Clear answer
             feedback_text,  # Final feedback
             gr.update(interactive=False, value="VIVA Complete"),
-            next_idx
+            next_idx,
+            None  # No audio
         )
 
 
@@ -701,6 +758,9 @@ with gr.Blocks(title="AnatomyBot - MBBS Anatomy Tutor") as demo:
                         current_question_display = gr.Markdown("### Question will appear here")
                         hint_display = gr.Markdown("💡 Hint will appear here")
                         
+                        # Audio player for question
+                        question_audio = gr.Audio(label="🔊 Listen to Question", autoplay=True, interactive=False)
+                        
                         student_answer = gr.Textbox(
                             label="Your Answer",
                             placeholder="Type your answer here...",
@@ -739,7 +799,8 @@ with gr.Blocks(title="AnatomyBot - MBBS Anatomy Tutor") as demo:
             viva_container, viva_status, viva_image,
             current_question_display, hint_display,
             student_answer, feedback_display, submit_answer_btn,
-            viva_questions_state
+            viva_questions_state,
+            question_audio  # Output audio
         ]
     ).then(
         fn=lambda: gr.update(selected=1),  # Switch to VIVA tab
@@ -755,7 +816,8 @@ with gr.Blocks(title="AnatomyBot - MBBS Anatomy Tutor") as demo:
         inputs=[student_answer, viva_questions_state, current_question_idx],
         outputs=[
             current_question_display, hint_display, student_answer,
-            feedback_display, submit_answer_btn, current_question_idx
+            feedback_display, submit_answer_btn, current_question_idx,
+            question_audio  # Output audio for next question
         ]
     )