Update app.py

app.py

@@ -1,9 +1,8 @@
 import streamlit as st
-import os
-from TTS.api import TTS
 import moviepy.editor as mp
-from io import BytesIO
 import soundfile as sf
+from io import BytesIO
+from TTS.api import TTS
 
 # Set up the model for text-to-speech (TTS)
 MODEL_NAME = "tts_models/en/ljspeech/tacotron2-DDC"  # Example TTS model; adjust as needed
@@ -11,16 +10,24 @@ tts = TTS(model_name=MODEL_NAME, progress_bar=True, gpu=False)
 
 # Function to extract audio from MP4 file
 def extract_audio_from_mp4(mp4_file):
-    video = mp.VideoFileClip(mp4_file)
-    audio = video.audio
-    audio_file = "temp_audio.wav"
-    audio.write_audiofile(audio_file)
-    return audio_file
+    try:
+        video = mp.VideoFileClip(mp4_file)
+        audio = video.audio
+        audio_file = "temp_audio.wav"
+        audio.write_audiofile(audio_file)
+        return audio_file
+    except Exception as e:
+        st.error(f"Error extracting audio from MP4: {e}")
+        return None
 
 # Function to load audio file
 def load_audio(file):
-    audio_data, sample_rate = sf.read(file)
-    return audio_data, sample_rate
+    try:
+        audio_data, sample_rate = sf.read(file)
+        return audio_data, sample_rate
+    except Exception as e:
+        st.error(f"Error loading audio: {e}")
+        return None, None
 
 # Function to save the generated audio to a file
 def save_audio(output_audio, sample_rate):
@@ -45,10 +52,11 @@ def main():
 
             # Extract audio from MP4
             audio_path = extract_audio_from_mp4("uploaded_video.mp4")
-            st.audio(audio_path, format="audio/wav")
-            
-            # Load audio for TTS processing
-            audio_data, sample_rate = load_audio(audio_path)
+            if audio_path:
+                st.audio(audio_path, format="audio/wav")
+
+                # Load audio for TTS processing
+                audio_data, sample_rate = load_audio(audio_path)
         else:
             # For audio files directly
             st.audio(audio_file, format=f"audio/{audio_file.type.split('/')[1]}")
@@ -59,17 +67,20 @@ def main():
             
             audio_data, sample_rate = load_audio("temp_audio.wav")
 
-        # Perform voice cloning (This assumes your TTS model supports some form of input)
-        try:
-            st.text("Processing your input...")
-            output_audio = tts.tts(audio_data)  # Pass the audio to your TTS model for cloning
-            output_path = save_audio(output_audio, sample_rate)
+        if audio_data is not None:
+            # Perform voice cloning (This assumes your TTS model supports some form of input)
+            try:
+                st.text("Processing your input...")
+                output_audio = tts.tts(audio_data)  # Pass the audio to your TTS model for cloning
+                output_path = save_audio(output_audio, sample_rate)
 
-            # Provide download link
-            st.audio(output_path, format="audio/wav")
-            st.markdown(f"[Download Cloned Voice](/{output_path})")
-        except Exception as e:
-            st.error(f"Error processing audio: {e}")
+                # Provide download link
+                st.audio(output_path, format="audio/wav")
+                st.markdown(f"[Download Cloned Voice](/{output_path})")
+            except Exception as e:
+                st.error(f"Error processing audio: {e}")
+        else:
+            st.error("No audio data to process.")
 
 if __name__ == "__main__":
     main()