Create app.py

app.py

@@ -0,0 +1,50 @@
+!pip install gradio groq openai-whisper gtts
+
+
+import os
+import gradio as gr
+from groq import Groq
+import whisper
+from gtts import gTTS
+import tempfile
+
+# Set up Groq API key
+os.environ['GROQ_API_KEY'] = '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'
+groq_client = Groq(api_key=os.environ.get('GROQ_API_KEY'))
+
+# Load Whisper model
+whisper_model = whisper.load_model("base")
+
+def process_audio(audio_file):
+    # Transcribe audio using Whisper
+    result = whisper_model.transcribe(audio_file)
+    user_text = result['text']
+
+    # Generate response using Llama 8b model with Groq API
+    chat_completion = groq_client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": user_text,
+            }
+        ],
+        model="llama3-8b-8192",
+    )
+    response_text = chat_completion.choices[0].message.content
+
+    # Convert response text to speech using gTTS
+    tts = gTTS(text=response_text, lang='en')
+    audio_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp3')
+    tts.save(audio_file.name)
+
+    return response_text, audio_file.name
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=process_audio,
+    inputs=gr.Audio(type="filepath"),
+    outputs=[gr.Textbox(label="Response"), gr.Audio(label="Response Audio")],
+    live=True
+)
+
+iface.launch()