Update app.py

app.py

@@ -0,0 +1,52 @@
+import os
+import whisper
+from groq import Groq
+from diffusers import StableDiffusionPipeline
+import gradio as gr
+import torch
+
+# Load Whisper model
+whisper_model = whisper.load_model("base")
+
+GROQ_API_KEY="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"
+client=Groq(api_key=GROQ_API_KEY)
+
+# Load Stable Diffusion pipeline
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+stable_diffusion_model = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5"
+).to(device)
+
+# Function to handle voice-to-image pipeline
+def voice_to_image(audio):
+    # Step 1: Transcribe audio to text using Whisper
+    transcription = whisper_model.transcribe(audio)
+    input_text = transcription["text"]
+
+    # Step 2: Query LLM using Groq API
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {"role": "user", "content": input_text},
+        ],
+        model="llama3-8b-8192",
+        stream=False,
+    )
+    response_text = chat_completion.choices[0].message.content
+
+    # Step 3: Generate image using Stable Diffusion
+    image = stable_diffusion_model(response_text).images[0]
+
+    return image
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=voice_to_image,
+    inputs=gr.Audio(type="filepath"),
+    outputs="image",
+    title="Real-Time Voice-to-Image Generator",
+    description="Transcribe voice input into an image using Whisper, Groq LLM, and Stable Diffusion."
+)
+
+# Launch Gradio app
+interface.launch()