Update app.py

app.py

@@ -1,14 +1,9 @@
 import gradio as gr
-
 from google.generativeai import GenerativeModel, configure
 from gtts import gTTS
 import speech_recognition as sr
 import os
 import tempfile
-import torch
-from torchvision import models, transforms
-from PIL import Image
-import json
 
 # ✅ Load API key from environment variable
 GOOGLE_API_KEY = os.getenv("GEMINI_API_KEY")
@@ -24,27 +19,28 @@ def transcribe_audio(audio_path):
     with sr.AudioFile(audio_path) as source:
         audio = recognizer.record(source)
     try:
-        return recognizer.recognize_google(audio, language='pa-IN')
+        return recognizer.recognize_google(audio, language='en-US')
     except sr.UnknownValueError:
-        return "❌ ਆਵਾਜ਼ ਨੂੰ ਸਮਝਿਆ ਨਹੀਂ ਜਾ ਸਕਿਆ।"
+        return "❌ Could not understand the audio."
     except sr.RequestError:
-        return "❌ ਗੂਗਲ ਸਪੀਚ ਐਪੀਆਈ ਨਾਲ ਕਨੇਕਟ ਨਹੀਂ ਹੋ ਸਕਿਆ।"
-        
+        return "❌ Could not connect to Google Speech API."
+
 def get_gemini_response(query):
     try:
-        response = gemini_model.generate_content(f"ਪੰਜਾਬੀ ਵਿੱਚ ਜਵਾਬ ਦਿਓ: {query}")
+        # Request Gemini model to answer in English
+        response = gemini_model.generate_content(f"Answer in English: {query}")
         return response.text.replace('*', '')
     except Exception as e:
-        return f"❌ Gemini ਤਰਫੋਂ ਗਲਤੀ: {str(e)}"
+        return f"❌ Error from Gemini: {str(e)}"
 
-def text_to_speech(text, lang='pa'):
+def text_to_speech(text, lang='en'):
     tts = gTTS(text=text, lang=lang)
     temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
     tts.save(temp_file.name)
     return temp_file.name
 
 # ---------------------------
-# Combined Function
+# Combined function to handle voice query
 # ---------------------------
 def handle_voice_query(audio_file):
     query = transcribe_audio(audio_file)
@@ -53,15 +49,15 @@ def handle_voice_query(audio_file):
     return query, response, audio_path
 
 with gr.Blocks() as demo:
-    gr.Markdown("# 🗣️ **ਆਵਾਜ਼ ਰਾਹੀਂ ਪੁੱਛੋ**")
-    gr.Markdown("### ਆਪਣਾ ਸਵਾਲ ਆਵਾਜ਼ ਰਾਹੀਂ ਪੁੱਛੋ (ਪੰਜਾਬੀ ਵਿੱਚ)")
-    audio_input = gr.Audio(type="filepath", label="🎤 ਸਵਾਲ ਬੋਲੋ")
-    query_text = gr.Textbox(label="🔍 ਬੋਲਿਆ ਗਿਆ ਸਵਾਲ")
-    gemini_response = gr.Textbox(label="📜 Gemini ਜਵਾਬ")
-    audio_output = gr.Audio(label="🔊 ਆਵਾਜ਼ੀ ਜਵਾਬ")
-    submit_btn = gr.Button("➡️ ਜਵਾਬ ਲਵੋ")
+    gr.Markdown("# 🗣️ **Ask by Voice**")
+    gr.Markdown("### Speak your question aloud (in English)")
+    audio_input = gr.Audio(type="filepath", label="🎤 Speak your question")
+    query_text = gr.Textbox(label="🔍 Spoken Question")
+    gemini_response = gr.Textbox(label="📜 Gemini Response")
+    audio_output = gr.Audio(label="🔊 Voice Response")
+    submit_btn = gr.Button("➡️ Get Answer")
     submit_btn.click(fn=handle_voice_query,
-                        inputs=[audio_input],
-                        outputs=[query_text, gemini_response, audio_output])
+                     inputs=[audio_input],
+                     outputs=[query_text, gemini_response, audio_output])
 
-demo.launch()
+demo.launch()