Update app.py

app.py

@@ -7,12 +7,10 @@ import openai
 
 prompt = "Type and press Enter"
 
-r = sr.Recognizer()
 
-
-def record_text(audio_file,prompt):
-    if len(prompt) == 0:
-        prompt = "Apply proper punctuations, upper case and lower case to the provided text."
+def record_text(audio_file):
+    r = sr.Recognizer()
+    
     sound = audio_file
     sound_type = sound.split(".")
     if sound_type[-1] == 'mp3':
@@ -32,12 +30,48 @@ def record_text(audio_file,prompt):
         
         MyText = r.recognize_google(audio2, language="en-US", key=None, show_all=False)
         MyText = MyText.lower()
-    return (MyText,prompt)
+    return (MyText)
+
+
+def api_calling(audio_file, prompt, api_key):
+    audio_text = record_text(audio_file)
+    if len(prompt) == 0:
+        prompt = "Apply proper punctuations, upper case and lower case to the provided text."
+    
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}"
+    }
+    payload = {
+        "model": "gpt-3.5-turbo",
+        "messages": [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": prompt
+                    },
+                    {
+                        "type": "text",
+                        "text": audio_text
+                        }
+                    }
+                ]
+            }
+        ],
+        "max_tokens": 1000
+    }
+    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+    audio_text_res = response.json()
+    return audio_text_res
+
+
 
 def message_and_history(audio_file,input, history, api_key):
     history = history or []
     input_text = "Type and press Enter"
-    output_text = record_text(audio_file,input)
+    output_text = api_calling(audio_file,input,api_key)
     
     if len(input_text) == 0:
         input_text = "Speech from the video."