Adding leageoflegends

.vscode/settings.json

@@ -0,0 +1,11 @@
+{
+    "files.exclude": {
+        "**/.git": true,
+        "**/.svn": true,
+        "**/.hg": true,
+        "**/CVS": true,
+        "**/.DS_Store": true,
+        "**/Thumbs.db": true
+    },
+    "hide-files.files": []
+}

leageoflegends/capture.py

@@ -0,0 +1,31 @@
+import os
+import time
+import pyautogui
+from PIL import Image
+
+# Folder
+folder = "frames"
+frames_dir = os.path.join(os.getcwd(), folder)
+os.makedirs(frames_dir, exist_ok=True)
+
+while True:
+
+    # Wait for Chrome to activate
+    time.sleep(2)
+
+    # Take a screenshot
+    screenshot = pyautogui.screenshot()
+
+    # Convert screenshot to RGB (JPEG does not support RGBA)
+    screenshot_rgb = screenshot.convert('RGB')
+
+    # Optional: Resize the image
+    max_size = 250
+    ratio = max_size / max(screenshot_rgb.size)
+    new_size = tuple([int(x * ratio) for x in screenshot_rgb.size])
+    resized_img = screenshot_rgb.resize(new_size, Image.LANCZOS)
+
+    # Save the frame as an image file
+    print("📸 Captured Chrome tab. Saving frame.")
+    path = f"{frames_dir}/frame.jpg"
+    resized_img.save(path)

leageoflegends/listen.py

@@ -0,0 +1,26 @@
+import os
+import time
+from playsound import playsound
+
+def find_latest_folder(base_path):
+    all_folders = [os.path.join(base_path, d) for d in os.listdir(base_path) if os.path.isdir(os.path.join(base_path, d))]
+    latest_folder = max(all_folders, key=os.path.getmtime)
+    return latest_folder
+
+def main():
+    base_path = 'narration'  # Base path to the narration folder
+    last_played_folder = None
+
+    while True:
+        latest_folder = find_latest_folder(base_path)
+        audio_file = os.path.join(latest_folder, 'audio.wav')
+
+        if os.path.exists(audio_file) and latest_folder != last_played_folder:
+            print(f"Playing audio from {audio_file}")
+            playsound(audio_file)
+            last_played_folder = latest_folder
+            # After the audio finishes, wait for a short period before checking for new folders
+            # time.sleep(2)
+
+if __name__ == "__main__":
+    main()

leageoflegends/narrator.py

@@ -0,0 +1,111 @@
+import os
+from openai import OpenAI
+import base64
+import json
+import time
+import simpleaudio as sa
+import errno
+from elevenlabs import generate, play, set_api_key, voices
+from playsound import playsound
+
+client = OpenAI()
+
+set_api_key(os.environ.get("ELEVENLABS_API_KEY"))
+
+def encode_image(image_path):
+    while True:
+        try:
+            with open(image_path, "rb") as image_file:
+                return base64.b64encode(image_file.read()).decode("utf-8")
+        except IOError as e:
+            if e.errno != errno.EACCES:
+                # Not a "file in use" error, re-raise
+                raise
+            # File is being written to, wait a bit and retry
+            time.sleep(0.1)
+
+
+def play_audio(text):
+    audio = generate(text, voice=os.environ.get("ELEVENLABS_VOICE_ID"))
+
+    unique_id = base64.urlsafe_b64encode(os.urandom(30)).decode("utf-8").rstrip("=")
+    dir_path = os.path.join("narration", unique_id)
+    os.makedirs(dir_path, exist_ok=True)
+    file_path = os.path.join(dir_path, "audio.wav")
+
+    with open(file_path, "wb") as f:
+        f.write(audio)
+
+    # play(audio)
+    # playsound(file_path)
+
+
+def generate_new_line(base64_image):
+    return [
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Describe this image"},
+                {
+                    "type": "image_url",
+                    "image_url": f"data:image/jpeg;base64,{base64_image}",
+                },
+            ],
+        },
+    ]
+
+
+def analyze_image(base64_image, script):
+    response = client.chat.completions.create(
+        model="gpt-4-vision-preview",
+        messages=[
+            {
+                "role": "system",
+                "content": """
+                You are real commentator, express more. 
+                Narrate with intensity.
+                You are watching a game. 
+                Don't repeat yourself. Comment in one line.
+                Focus on the minute details.
+                Mention the individual by what the text near the head says.
+                Focus on what's happenning in the game.
+                Comments not more than 20 words.
+                Don't explain about the game, but focus on activities in the game. 
+                """,
+            },
+        ]
+        + script
+        + generate_new_line(base64_image),
+        max_tokens=500,
+    )
+    response_text = response.choices[0].message.content
+    return response_text
+
+
+def main():
+    script = []
+
+    while True:
+        # path to your image
+        image_path = os.path.join(os.getcwd(), "./frames/frame.jpg")
+
+        # getting the base64 encoding
+        base64_image = encode_image(image_path)
+
+        # analyze posture
+        print("👀 Mervin Praison is watching...")
+        analysis = analyze_image(base64_image, script=script)
+
+        print("🎙️ Mervin Praison says:")
+        print(analysis)
+
+        play_audio(analysis)
+
+        script = script + [{"role": "assistant", "content": analysis}]
+
+        # wait for 5 seconds
+        # time.sleep(1)
+
+
+if __name__ == "__main__":
+    main()

narrator.py

@@ -6,6 +6,7 @@ import time
 import simpleaudio as sa
 import errno
 from elevenlabs import generate, play, set_api_key, voices
+from playsound import playsound
 
 client = OpenAI()
 
@@ -36,6 +37,7 @@ def play_audio(text):
         f.write(audio)
 
     play(audio)
+    playsound(file_path)
 
 
 def generate_new_line(base64_image):
@@ -84,10 +86,10 @@ def main():
         base64_image = encode_image(image_path)
 
         # analyze posture
-        print("👀 David is watching...")
+        print("👀 Mervin Praison is watching...")
         analysis = analyze_image(base64_image, script=script)
 
-        print("🎙️ David says:")
+        print("🎙️ Mervin Praison says:")
         print(analysis)
 
         play_audio(analysis)

requirements.txt

@@ -39,3 +39,5 @@ typing_extensions==4.8.0
 urllib3==2.0.7
 wcwidth==0.2.10
 websockets==12.0
+playsound
+pyautogui