update

app.py

@@ -9,6 +9,8 @@ import scipy.io.wavfile as wavfile
 from sklearn.preprocessing import StandardScaler
 import time
 import os
+from gtts import gTTS
+import gradio as gr
 
 # ------------------- Speech Emotion Recognition Model -------------------
 class SpeechEmotionRecognizer:
@@ -47,11 +49,23 @@ class FacialEmotionRecognizer:
         return self.labels[emotion_idx]
 
 # ------------------- Utility Functions -------------------
+
+
 def speak(text):
-    engine = pyttsx3.init()
-    engine.setProperty('rate', 150)
-    engine.say(text)
-    engine.runAndWait()
+    if not text.strip():
+        return None
+    tts = gTTS(text)
+    tts.save("output.mp3")
+    return "output.mp3"
+
+iface = gr.Interface(
+    fn=speak,
+    inputs=gr.Textbox(lines=2, label="Enter text"),
+    outputs=gr.Audio(type="filepath", label="Speech Output"),
+    title="Text to Speech"
+)
+
+iface.launch()
 
 def record_audio(duration=3, fs=22050):
     print("Recording audio...")