Update app.py

app.py

@@ -3,10 +3,14 @@ import requests
 import google.generativeai as genai
 import gradio as gr
 from tempfile import NamedTemporaryFile
+from google.cloud import speech
 
 # Configure your Google Generative AI API key
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
+# Set up Google Cloud credentials for Speech-to-Text
+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "path_to_your_google_cloud_credentials.json"
+
 # Create the model
 generation_config = {
     "temperature": 1,
@@ -42,9 +46,27 @@ def chat_and_tts_text(user_input, history):
         return history, f"Error: {str(e)}"
 
 def convert_audio_to_text(audio_file):
-    # This is a placeholder function. Replace with actual implementation.
-    # For now, we assume the function just returns a dummy text.
-    return "Sample text from audio"
+    try:
+        client = speech.SpeechClient()
+        
+        with open(audio_file.name, "rb") as audio:
+            content = audio.read()
+
+        audio = speech.RecognitionAudio(content=content)
+        config = speech.RecognitionConfig(
+            encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
+            sample_rate_hertz=16000,
+            language_code="en-US",
+        )
+
+        response = client.recognize(config=config, audio=audio)
+        
+        # Assuming the audio contains only one speech segment
+        transcript = response.results[0].alternatives[0].transcript
+        return transcript
+
+    except Exception as e:
+        return f"Error in audio to text conversion: {str(e)}"
 
 def chat_and_tts_audio(audio_file, history):
     try: