trying

app.py

@@ -41,28 +41,40 @@ def video_to_frames(video_file):
     return base64Frames, video_filename, video_duration
 
 
-def frames_to_story(base64Frames, prompt):
-    PROMPT_MESSAGES = [
-        {
-            "role": "user",
-            "content": [
-                prompt,
-                *map(lambda x: {"image": x, "resize": 768},
-                     base64Frames[0::25]),
-            ],
-        },
-    ]
+def frames_to_story(frames, prompt):
+
+  try:
+    # Format prompt with Markdown
+    prompt = f"**Summary:** {prompt}"
+    
+    messages = [{
+      "role": "user",
+      "content": [prompt, *frames]  
+    }]
+    
     params = {
-        "model": "gpt-4-vision-preview",
-        "messages": PROMPT_MESSAGES,
-        "api_key": os.environ["OPENAI_API_KEY"],
-        "headers": {"Openai-Version": "2020-11-07"},
-        "max_tokens": 500,
+      "model": "gpt-3.5-turbo",
+      "messages": messages,  
+      "max_tokens": 100,
     }
 
-    result = openai.ChatCompletion.create(**params)
-    print(result.choices[0].message.content)
-    return result.choices[0].message.content
+    response = openai.Chat.create(**params)
+    
+    story = response.choices[0].message.content
+
+    # Generate audio stream from text
+    audio_bytes = text_to_audio(story)
+
+    # Display word count
+    word_count = len(story.split())
+    st.write(f"**Words:** {word_count}")
+
+    return story, audio_bytes
+
+  except Exception as e:
+    st.error("Error generating story:", e)
+    return None, None
+
 
 
 def text_to_audio(text):