Update app.py

app.py

@@ -5,6 +5,7 @@ import os
 from PIL import Image
 import ffmpeg
 from pydub import AudioSegment
+from gtts import gTTS
 
 import numpy as np
 import soundfile as sf
@@ -39,7 +40,13 @@ def run_infrence(input_image,input_audio):
     pil_image.save(filename)
 
     #Save input audio
-    save_audio_mp3(input_audio, "sample_data/uploaded_audio.mp3")
+    #save_audio_mp3(input_audio, "sample_data/uploaded_audio.mp3")
+
+    if input_text:
+        tts = gTTS(input_text, lang='en', tld='com.au')
+        tts.save("sample_data/uploaded_audio.mp3")
+    else:
+        save_audio_mp3(input_audio, "sample_data/uploaded_audio.mp3")
 
     command = f'python3 inference.py --checkpoint_path checkpoints/wav2lip_gan.pth --face sample_data/uploaded_image.png --audio sample_data/uploaded_audio.mp3'
     process = subprocess.Popen(command, stdout=subprocess.PIPE, shell=True)
@@ -53,8 +60,9 @@ def run():
         with gr.Group():    
             with gr.Row():
                 input_image = gr.Image(label="Input Image")
-                input_audio = gr.Audio(label="Input Audio")
-                video_out = gr.Video(show_label=True,label="Output")
+                input_audio = gr.Audio(label="Input Audio (Optional)")
+                input_text = gr.Textbox(label="Input Text (Optional)", placeholder="Enter text to convert to audio")
+                video_out = gr.Video(show_label=True, label="Output")
             with gr.Row():
                 btn = gr.Button("Generate")