Update app.py

app.py

@@ -1,4 +1,4 @@
-import streamlit as st
+import gradio as gr
 import edge_tts
 import asyncio
 import tempfile
@@ -11,7 +11,7 @@ import random
 
 default_lang = "en"
 
-engines = {default_lang: Model(default_lang)}
+engines = { default_lang: Model(default_lang) }
 
 def transcribe(audio):
     lang = "en"
@@ -34,6 +34,7 @@ Respond in a normal, conversational manner while being friendly and helpful.
 """
 
 def models(text, seed=42):
+
     seed = int(randomize_seed_fn(seed))
     generator = torch.Generator().manual_seed(seed)  
     
@@ -61,25 +62,35 @@ async def respond(audio, model, seed):
     with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
         tmp_path = tmp_file.name
         await communicate.save(tmp_path)
-    return tmp_path
+    yield tmp_path
 
 DESCRIPTION = """ # <center><b>JARVIS⚡</b></center>
         ### <center>A personal Assistant of Tony Stark for YOU
         ### <center>Voice Chat with your personal Assistant</center>
         """
 
-st.markdown(DESCRIPTION)
-st.title("JARVIS")
-
-uploaded_file = st.file_uploader("Upload audio file", type=["wav"])
-seed = st.slider("Seed", min_value=0, max_value=999999, value=0)
-if uploaded_file is not None:
-    # Convert the uploaded file to a BytesIO object
-    audio_bytes = uploaded_file.read()
-
-    # Process the audio using the respond function
-    response_path = asyncio.run(respond(audio_bytes, models, seed))
-
-    # Display the audio response
-    st.audio(response_path, format="audio/wav")
-    os.remove(response_path)
+with gr.Blocks(css="style.css") as demo:    
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+        seed = gr.Slider(
+        label="Seed",
+        minimum=0,
+        maximum=999999,
+        step=1,
+        value=0,
+        visible=False
+        )
+        input = gr.Audio(label="User", sources="microphone", type="filepath", waveform_options=False)
+        output = gr.Audio(label="AI", type="filepath",
+                        interactive=False,
+                        autoplay=True,
+                        elem_classes="audio")
+        gr.Interface(
+            batch=True,
+            max_batch_size=10, 
+            fn=respond, 
+            inputs=[input, select, seed],
+            outputs=[output], live=True)  
+        
+if __name__ == "__main__":
+    demo.queue(max_size=200).launch()