Create app.py

app.py

@@ -0,0 +1,126 @@
+# Import necessary libraries
+import whisper
+import os
+from gtts import gTTS
+import gradio as gr
+from groq import Groq
+import time
+
+# Load Whisper tiny model for faster transcription
+model = whisper.load_model("tiny")
+
+# Set up Groq API client (ensure GROQ_API_KEY is set in your environment)
+GROQ_API_KEY = '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'
+client = Groq(api_key=GROQ_API_KEY)
+
+# Function to get the LLM response from Groq with error handling and timing
+def get_llm_response(user_input):
+    try:
+        start_time = time.time()  # Start time to track API delay
+        chat_completion = client.chat.completions.create(
+            messages=[{"role": "user", "content": user_input}],
+            model="llama3-8b-8192",  # Replace with your desired model
+        )
+        response_time = time.time() - start_time  # Calculate response time
+
+        # If it takes too long, return a warning
+        if response_time > 10:  # You can adjust the timeout threshold
+            return "The response took too long, please try again."
+
+        return chat_completion.choices[0].message.content
+
+    except Exception as e:
+        return f"Error in LLM response: {str(e)}"
+
+# Function to convert text to speech using gTTS
+def text_to_speech(text, output_audio="output_audio.mp3"):
+    try:
+        tts = gTTS(text)
+        tts.save(output_audio)
+        return output_audio
+    except Exception as e:
+        return f"Error in Text-to-Speech: {str(e)}"
+
+# Function for Text to Voice
+def text_to_voice(user_text, voice="en"):
+    output_audio = text_to_speech(user_text)
+    return output_audio  # Return only audio response
+
+# Main chatbot function to handle audio or text input and output
+def chatbot(audio=None, user_text=None, voice="en"):
+    try:
+        # Step 1: If audio is provided, transcribe the audio using Whisper
+        if audio:
+            result = model.transcribe(audio)
+            user_text = result["text"]
+
+            # Check if transcription is empty
+            if not user_text.strip():
+                return "No transcription found. Please try again.", None
+
+        # Step 2: Get LLM response from Groq
+        response_text = get_llm_response(user_text)
+
+        # Step 3: Convert the response text to speech
+        if response_text.startswith("Error"):
+            return response_text, None
+
+        output_audio = text_to_speech(response_text)
+
+        if output_audio.startswith("Error"):
+            return output_audio, None
+
+        return response_text, output_audio
+
+    except Exception as e:
+        return f"Error in chatbot processing: {str(e)}", None
+
+# Define the About app section
+def about_app():
+    about_text = """
+    **Voicesy AI** is a real-time chatbot and voice conversion app built by Hamaad Ayub Khan.
+    It uses advanced AI models for transcription and language processing. This app allows users 
+    to interact through both voice and text, converting text to speech and providing quick, 
+    intelligent responses.
+    **Disclaimer**: While the AI is powerful, it may make mistakes, and users should double-check critical information.
+    """
+    return about_text
+
+# Gradio interface for real-time interaction with voice selection
+with gr.Blocks(css="style.css") as iface:  # Include the CSS file here
+    gr.Markdown("# Voicesy AI")
+
+    # Tab for Voice to Voice
+    with gr.Tab("Voice to Voice"):
+        audio_input = gr.Audio(type="filepath", label="Input Audio (optional)")  # Input from mic or file
+        text_input = gr.Textbox(placeholder="Type your message here...", label="Input Text (optional)")
+        voice_selection = gr.Dropdown(choices=["en", "en-uk", "en-au", "fr", "de", "es"], label="Select Voice", value="en")  # Voice selection
+        
+        output_text = gr.Textbox(label="AI Response")
+        output_audio = gr.Audio(type="filepath", label="AI Audio Response")
+        
+        # Button for Voice to Voice
+        voice_to_voice_button = gr.Button("Voice to Voice")
+        
+        # Define button actions
+        voice_to_voice_button.click(chatbot, inputs=[audio_input, text_input, voice_selection], outputs=[output_text, output_audio])
+
+    # Tab for Text to Speech
+    with gr.Tab("Text to Speech"):
+        text_input = gr.Textbox(placeholder="Type your message here...", label="Input Text")
+        voice_selection = gr.Dropdown(choices=["en", "en-uk", "en-au", "fr", "de", "es"], label="Select Voice", value="en")
+        output_audio = gr.Audio(type="filepath", label="AI Audio Response")
+
+        # Button to convert text to speech
+        convert_button = gr.Button("Convert to Speech")
+        convert_button.click(text_to_voice, inputs=[text_input, voice_selection], outputs=[output_audio])  
+
+    # Tab for About App
+    with gr.Tab("About App"):
+        about = gr.Markdown(about_app())
+
+    # Set up the footer
+    gr.Markdown("Voicesy AI | [Instagram](https://instagram.com/hamaadayubkhan) | [GitHub](https://github.com/hakgs1234) | [LinkedIn](https://www.linkedin.com/in/hamaadayubkhan)")
+
+# Launch the Gradio app
+iface.launch()