Create app.py

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+import torch
+import whisper
+# **Combine Interfaces in Tabs**
+with gr.Blocks() as demo:
+    gr.Markdown("## Unified Gradio App for Text-to-Image and Speech Processing")
+
+    with gr.Tab("Text-to-Image"):
+        gr.Markdown("### Generate Images from Text")
+        text_to_image_prompt = gr.Textbox(label="Enter your prompt", placeholder="Describe the image you want...")
+        text_to_image_output = gr.Image(label="Generated Image", type="pil")
+        text_to_image_button = gr.Button("Generate Image")
+        text_to_image_button.click(generate_image, inputs=text_to_image_prompt, outputs=text_to_image_output)
+
+    with gr.Tab("Speech Processing"):
+        gr.Markdown("### Speech-to-Text and Text-to-Speech")
+        audio_input = gr.Audio(type="filepath", label="Upload voice sample (WAV file)")
+        tts_text_input = gr.Textbox(label="Text to speak (optional if transcribing)")
+        transcribe_checkbox = gr.Checkbox(label="Transcribe input audio")
+        audio_output = gr.Audio(label="Synthesized Voice Output")
+        transcription_output = gr.Textbox(label="Transcription/Status")
+        process_button = gr.Button("Process Voice")
+        process_button.click(process_voice, 
+                             inputs=[audio_input, tts_text_input, transcribe_checkbox], 
+                             outputs=[audio_output, transcription_output])
+
+# Launch the app
+demo.launch(share=True)