Create app.py

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import pytesseract
+import cv2
+import numpy as np
+from PIL import Image
+from gtts import gTTS
+import os
+
+def preprocess(image):
+    img = np.array(image)
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    blur = cv2.GaussianBlur(gray, (5,5), 0)
+    thresh = cv2.threshold(
+        blur, 0, 255,
+        cv2.THRESH_BINARY + cv2.THRESH_OTSU
+    )[1]
+    return thresh
+
+def extract_and_speak(image):
+    processed = preprocess(image)
+    
+    text = pytesseract.image_to_string(processed, lang="eng")
+    
+    if text.strip() == "":
+        return "No readable text found.", None
+    
+    tts = gTTS(text)
+    tts.save("output.mp3")
+    
+    return text, "output.mp3"
+
+interface = gr.Interface(
+    fn=extract_and_speak,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Textbox(label="Extracted Text"),
+        gr.Audio(label="Text-to-Speech Output")
+    ],
+    title="GabAI - AI Assistive Reading System",
+    description="Upload an image containing printed text. The system extracts the text and converts it into speech."
+)
+
+interface.launch()