Update app.py

app.py

@@ -1,15 +1,13 @@
 import gradio as gr
 import google.generativeai as genai
 from PIL import Image
-import io
-from gtts import gTTS
 
 # Configure Gemini API (hardcoded as you requested)
 genai.configure(api_key="AIzaSyB6JYzYNfi8ak7g6526raHQ08YPMiC5Wic")
 
 def interpret_sign(image: Image.Image):
     if image is None:
-        return "Please upload or capture an image.", None
+        return "Please upload or capture an image."
 
     try:
         # Prepare prompt
@@ -34,28 +32,19 @@ def interpret_sign(image: Image.Image):
         if not text:
             text = getattr(response, "text", None)
         if not text or not text.strip():
-            return "Could not interpret the sign.", None
+            return "Could not interpret the sign."
 
-        # Generate TTS audio
-        tts = gTTS(text=text, lang='en', slow=False)
-        audio_fp = io.BytesIO()
-        tts.write_to_fp(audio_fp)
-        audio_fp.seek(0)
-
-        return text, (audio_fp, "audio/mp3")
+        return text
     except Exception as e:
-        return f"Error: {str(e)}", None
+        return f"Error: {str(e)}"
 
 # Gradio UI
 demo = gr.Interface(
     fn=interpret_sign,
     inputs=gr.Image(label="Sign Image", sources=["upload", "webcam"], type="pil"),
-    outputs=[
-        gr.Textbox(label="Interpretation"),
-        gr.Audio(label="Audio", type="filepath")
-    ],
+    outputs=gr.Textbox(label="Interpretation"),
     title="Sign Language Interpreter",
-    description="Upload or capture an image of a sign language gesture. The app will interpret the sign and provide an audio output."
+    description="Upload or capture an image of a sign language gesture. The app will interpret the sign."
 )
 
 if __name__ == "__main__":