Update app.py

app.py

@@ -1,3 +1,6 @@
+import os
+os.environ["TTS_ACCEPT_TOS"] = "1"  # Add this line to accept the TOS
+
 import gradio as gr
 import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
@@ -77,20 +80,30 @@ def process_audio(audio_file, translate_language, tts_language):
         return f"An error occurred: {e}", None
 
 # Gradio Interface
-interface = gr.Interface(
-    fn=process_audio,
-    inputs=[
-        gr.Audio(type="filepath", label="Upload or Record Audio"),
-        gr.Dropdown(choices=list(languages.keys()), label="Translation Language "),
-        gr.Dropdown(choices=list(languages.values()), label="TTS Synthesis Language (XTTS)")
-    ],
-    outputs=[
-        gr.Textbox(label="Translated Text"),
-        gr.Audio(label="Generated Audio")
-    ],
-    title="AI VOX LAB POC",
-    description="Upload/record audio, translate, and get synthesized speech!"
-)
+with gr.Blocks() as interface:
+    gr.Markdown("# AI VOX LAB POC")
+    gr.Markdown("Upload/record audio, translate, and get synthesized speech!")
+    
+    # Add the image here
+    gr.Image(value="/Users/mac/Desktop/VOX_AI/logo_transparent_background.png", label="App Logo", show_label=False, width=700, height=250)
+    
+    with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="Upload or Record Audio")
+        translate_lang = gr.Dropdown(choices=list(languages.keys()), label="Translation Language")
+        tts_lang = gr.Dropdown(choices=list(languages.values()), label="TTS Synthesis Language")
+    
+    with gr.Row():
+        translate_button = gr.Button("Translate and Synthesize")
+    
+    with gr.Row():
+        text_output = gr.Textbox(label="Translated Text")
+        audio_output = gr.Audio(label="Generated Audio")
+    
+    translate_button.click(
+        fn=process_audio, 
+        inputs=[audio_input, translate_lang, tts_lang], 
+        outputs=[text_output, audio_output]
+    )
 
 # Launch the App
 if __name__ == "__main__":