fixed audio?

app.py

@@ -19,21 +19,18 @@ def text_to_speech(message):
     API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
     headers = {"Authorization": f"Bearer {HUGGINGFACE_API_TOKEN}"}
     payloads = {
-        "inputs": message
+        "inputs":message
     }
 
     response = requests.post(API_URL, headers=headers, json=payloads)
-    if response.status_code == 200:
-        # Return the audio content directly
-        return response.content
-    else:
-        # Handle errors or return a default error message/audio
-        return None
-
+    with open('audio.flac', 'wb') as file:
+        file.write(response.content)
+        
 def main():
     st.set_page_config(page_title="Image to Text", page_icon="🎙️")
 
     st.header("Image to Text")
+    # Image.
     image = "narrator.jpeg"
     left_co, cent_co, last_co = st.columns(3)
     with cent_co:
@@ -41,17 +38,19 @@ def main():
     uploaded_file = st.file_uploader("Choose an image: ", type=["jpg", "jpeg", "png"])
 
     if uploaded_file is not None:
+        print(uploaded_file)
         bytes_data = uploaded_file.getvalue()
         with open(uploaded_file.name, "wb") as file:
             file.write(bytes_data)
-        st.image(uploaded_file, caption='Uploaded image', use_column_width=True)
-        scenario = img_to_text(uploaded_file.name)
-        
-        audio_content = text_to_speech(scenario)
-        if audio_content:
-            st.audio(audio_content, format="audio/flac")
-        else:
-            st.error("Failed to generate audio.")
+            st.image(uploaded_file, caption='Uploaded image', use_column_width=True)
+            scenario=img_to_text(uploaded_file.name)
+            text_to_speech(scenario)
+
+            with st.expander("scenatio"):
+                st.write(scenario)
+            
+            st.audio("audio.flac")
+
 
 if __name__== "__main__":
     main()