Create app.py

app.py

@@ -0,0 +1,54 @@
+import gradio as gr
+import asyncio
+import edge_tts
+import speech_recognition as sr
+from pydub import AudioSegment
+from pydub.playback import play
+import os
+from huggingface_hub import InferenceClient
+import whisper
+import torch
+from io import BytesIO
+import tempfile
+
+# Get the Hugging Face token from environment variable
+hf_token = os.environ.get("HF_TOKEN")
+if not hf_token:
+    raise ValueError("HF_TOKEN environment variable is not set")
+
+# Initialize the Hugging Face Inference Client
+client = InferenceClient(
+    "mistralai/Mistral-Nemo-Instruct-2407",
+    token=hf_token
+)
+
+# Load the Whisper model
+whisper_model = whisper.load_model("base", device='cuda')
+
+# Initialize an empty chat history
+chat_history = []
+
+# ... (rest of the functions remain the same) ...
+
+# Define the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# AI Voice Assistant")
+    
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(source="microphone", type="filepath", label="Speak here")
+            text_input = gr.Textbox(label="Or type your message here")
+        
+        with gr.Column():
+            chat_output = gr.Textbox(label="AI Response")
+            audio_output = gr.Audio(label="AI Voice Response")
+    
+    audio_button = gr.Button("Send Audio")
+    text_button = gr.Button("Send Text")
+    
+    audio_button.click(transcribe_and_chat, inputs=audio_input, outputs=[chat_output, audio_output])
+    text_button.click(lambda x: asyncio.run(chat_with_ai(x, [])), inputs=text_input, outputs=[chat_output, audio_output])
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)