use gtts

app.py

@@ -15,8 +15,8 @@ from langchain.chains import RetrievalQA, ConversationalRetrievalChain
 from langchain_groq import ChatGroq
 from langchain.memory import ConversationBufferMemory
 
-os.system("apt-get update")
-os.system("apt-get install -y espeak")
+from gtts import gTTS
+
 def load_groq_api_key():
     groq_api_key = os.getenv("GROQ_API_KEY") 
     if not groq_api_key:
@@ -92,12 +92,23 @@ def init_document_chatbot(knowledgeBase):
     )
 
 
-# 🔹 Convert Summary to Audio
+
+
 def text_to_speech(text):
-    engine = pyttsx3.init()
-    engine.save_to_file(text, "summary_audio.mp3")
-    engine.runAndWait()
-    return "summary_audio.mp3"
+    try:
+        # Create audio file with gTTS
+        tts = gTTS(text=text, lang='en')
+        audio_path = "/tmp/summary_audio.mp3"  # Use /tmp/ for Hugging Face Spaces
+        tts.save(audio_path)
+        
+        # Verify file was created
+        if os.path.exists(audio_path):
+            return audio_path
+        else:
+            raise Exception("Audio file not created")
+    except Exception as e:
+        print(f"Error in gTTS: {e}")
+        return None    
 
 
 # 🔹 Generate WordCloud