Create app.py

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+import torch
+from transformers import pipeline
+from gtts import gTTS
+import tempfile
+import os
+from groq import Groq
+
+# Load the Whisper model from Hugging Face
+device = "cuda" if torch.cuda.is_available() else "cpu"
+whisper_model = pipeline("automatic-speech-recognition", model="openai/whisper-base", device=device)
+
+# Initialize Groq client
+client = Groq(api_key="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")
+
+# Function to handle the voice-to-voice conversation
+def voice_to_voice_conversation(audio):
+    # Read and transcribe audio using Whisper
+    transcription = whisper_model(audio)["text"]
+
+    # Get response from Groq API using Llama 8b
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": transcription}],
+        model="llama3-8b-8192",
+    )
+    response_text = chat_completion.choices[0].message.content
+
+    # Convert text to speech using GTTS and save to a temporary file
+    tts = gTTS(response_text)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tts.save(tmp_file.name)
+        tmp_file_path = tmp_file.name
+
+    # Load the generated speech as an audio file for Gradio
+    return transcription, tmp_file_path
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=voice_to_voice_conversation,
+    inputs=gr.Audio(type="filepath"),
+    outputs=[gr.Textbox(label="Transcription"), gr.Audio(label="Response Audio")],
+    title="Voice-to-Voice Chatbot",
+    description="Speak into the microphone, and the chatbot will respond with a generated voice message.",
+    live=False
+)
+
+# Launch the interface
+interface.launch()