Update app.py

app.py

@@ -1,6 +1,9 @@
 # import part
 import streamlit as st
 from transformers import pipeline
+from gtts import gTTS
+import io
+
 
 # function part
 # img2text
@@ -9,6 +12,7 @@ def img2text(url):
     text = image_to_text_model(url)[0]["generated_text"]
     return text
 
+
 # text2story
 def text2story(text):
     pipe = pipeline(
@@ -32,12 +36,13 @@ def text2story(text):
     target_length = min(max(len(story.split()), 50), 150)
     return " ".join(story.split()[:target_length])
 
-
 # text2audio
 def text2audio(story_text):
-    pipe = pipeline("text-to-audio", model="Matthijs/mms-tts-eng")
-    audio_data = pipe(story_text)
-    return audio_data
+    tts = gTTS(text=story_text, lang='en')
+    audio_bytes = io.BytesIO()
+    tts.write_to_fp(audio_bytes)
+    audio_bytes.seek(0)
+    return audio_bytes
 
 
 def main():
@@ -105,9 +110,7 @@ def main():
 
             # Auto-play the audio
             st.audio(audio_data['audio'], 
-                    format="audio/wav",
-                    start_time=0,
-                    sample_rate=audio_data['sampling_rate'],
+                    format="audio/mp3",
                     autoplay=True) 
 
 if __name__ == "__main__":