Update app.py

app.py

@@ -4,6 +4,8 @@ from transformers import pipeline
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 import PyPDF2
+import pyttsx3
+import time
 
 # Load local models for inference
 stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
@@ -12,6 +14,14 @@ conversation_model = pipeline("text-generation", model="facebook/blenderbot-400M
 # Load a pre-trained model for vector embeddings
 embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
 
+# Text-to-Speech engine setup
+tts_engine = pyttsx3.init()
+
+def speak_text(text):
+    """Speak the given text using TTS engine."""
+    tts_engine.say(text)
+    tts_engine.runAndWait()
+
 # Parse PDF and create resume content
 def parse_resume(pdf):
     """Extract text from an uploaded PDF file."""
@@ -55,21 +65,32 @@ class MockInterview:
         self.resume_embeddings = process_resume(resume)
         self.job_desc_embedding = process_job_description(job_desc)
         self.interview_active = True
-        return "Resume and job description processed. Interview is ready to start."
+        return "Resume and job description processed. Starting the interview."
+
+    def start_interview(self):
+        if not self.interview_active:
+            return "Please upload your resume and job description first."
+        question = "Tell me about yourself."
+        speak_text(question)
+        return question
 
     def conduct_interview(self, audio_file):
         if not self.interview_active:
             return "Please upload your resume and job description first.", ""
 
-        transcription = stt_model(audio_file)["text"]  # Transcribe audio
+        # Transcribe audio
+        transcription = stt_model(audio_file)["text"]
         if not transcription.strip():
             return "No audio detected. Please try again.", ""
 
+        # Generate next question
         question = generate_question(transcription, self.resume_embeddings)
+        speak_text(question)
         return transcription, question
 
     def end_interview(self):
         self.interview_active = False
+        speak_text("Thank you for participating in the interview. Goodbye!")
         return "Interview ended. Thank you for participating."
 
 mock_interview = MockInterview()
@@ -77,6 +98,9 @@ mock_interview = MockInterview()
 def upload_inputs(resume, job_desc):
     return mock_interview.upload_inputs(resume, job_desc)
 
+def start_interview():
+    return mock_interview.start_interview()
+
 def conduct_interview(audio_file):
     return mock_interview.conduct_interview(audio_file)
 
@@ -86,7 +110,7 @@ def end_interview():
 interface = gr.Blocks()
 with interface:
     gr.Markdown("""# Mock Interview AI
-Upload your resume and job description, then engage in a realistic interview simulation.""")
+Upload your resume and job description, then engage in a realistic audio-based interview simulation.""")
 
     with gr.Row():
         resume_input = gr.File(label="Upload Resume (PDF)")
@@ -100,9 +124,9 @@ Upload your resume and job description, then engage in a realistic interview sim
         submit_button = gr.Button("Submit Response")
         end_button = gr.Button("End Interview")
 
-    upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[transcription_output])
+    upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[question_output])
     submit_button.click(conduct_interview, inputs=[audio_input], outputs=[transcription_output, question_output])
-    end_button.click(end_interview, outputs=[transcription_output])
+    end_button.click(end_interview, outputs=[question_output])
 
 if __name__ == "__main__":
     interface.launch()