Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import os
 import requests
 import torch
+import zipfile
 from TTS.api import TTS
 from pydub import AudioSegment
 
@@ -28,6 +29,15 @@ def download_audio_file(url):
         print(f"Error downloading audio file: {e}")
         return None
 
+def extract_zip_file(zip_file):
+    try:
+        with zipfile.ZipFile(zip_file, 'r') as zip_ref:
+            zip_ref.extractall()
+        return True
+    except zipfile.BadZipfile as e:
+        print(f"Error extracting zip file: {e}")
+        return False
+
 def convert_to_wav(input_audio_file):
     file_extension = os.path.splitext(input_audio_file)[-1].lower()
     if file_extension!= ".wav":
@@ -45,13 +55,21 @@ def synthesize_text(text, input_audio_file, language):
 def clone(text, input_file, language):
     if input_file is None:
         return None
-    input_audio_file = input_file.name
+    if input_file.name.endswith(".zip"):
+        if extract_zip_file(input_file):
+            input_audio_file = [f for f in os.listdir('.') if os.path.isfile(f) and f.endswith(tuple(AUDIO_FORMATS))]
+            if len(input_audio_file) == 1:
+                input_audio_file = input_audio_file[0]
+            else:
+                return "Error: Please select a single audio file from the extracted files."
+    else:
+        input_audio_file = input_file.name
     output_file_path = synthesize_text(text, input_audio_file, language)
     return output_file_path
 
 iface = gr.Interface(
     fn=clone,
-    inputs=["text", gr.File(label="Input File", file_types=AUDIO_FORMATS), gr.Dropdown(choices=LANGUAGES, label="Language")],
+    inputs=["text", gr.File(label="Input File", file_types=[".zip", *AUDIO_FORMATS]), gr.Dropdown(choices=LANGUAGES, label="Language")],
     outputs=gr.Audio(type='filepath'),
     title='Voice Clone',
     description=""" by [Angetyde](https://youtube.com/@Angetyde?si=7nusP31nTumIkPTF) and [Tony Assi](https://www.tonyassi.com/ ) use this colab with caution <3. """,