Create app.py

app.py

@@ -0,0 +1,42 @@
+import streamlit as st 
+import os 
+import requests
+import io
+from PIL import Image
+
+api_token = os.environ.get("api_token")
+API_URL_WH = "https://api-inference.huggingface.co/models/openai/whisper-large-v3"
+API_URL = "https://api-inference.huggingface.co/models/ehristoforu/dalle-3-xl"
+headers = {"Authorization": f"Bearer {api_token}"}
+st.title("Realtime Text2Image Voice")
+type = st.selectbox(
+    'Choose input type',
+    ("Text", "Voice")
+)
+
+def imquery(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.content
+
+def generate_image(prompt):
+    image_bytes = imquery({
+    	"inputs": prompt,
+    })
+    return image_bytes
+
+if type == "Text":
+    prompt = st.text_input("Enter prompt")
+    out = imquery(prompt)
+    st.image(out)
+else:
+    prompt = st.file_uploader("Paste your audiofile", type=["mp3", "m4a", "wav"])
+
+    def query(filename):
+        with open(filename, "rb") as f:
+            data = f.read()
+        response = requests.post(API_URL_WH, headers=headers, data=data)
+        return response.json()
+        
+    output = query(prompt)
+    imoo = generate_image(output)
+    st.image(imoo)