feat: grabs screenshot instead webcam

sarcastic technical lead prompt

.gitignore

@@ -2,3 +2,5 @@
 /venv
 /frames
 /narration
+/screeshots
+.vscode

README.md

@@ -1,5 +1,9 @@
-# narrator
+# sarcastic narrator
+Sarcastic David Attenborough narrates what you are doing based on your screen
 
+
+Forked from this project:
+https://github.com/cbh123/narrator
 David Attenborough narrates your life.
 https://twitter.com/charliebholtz/status/1724815159590293764
 

capture.py

@@ -1,46 +1,26 @@
-import cv2
+from PIL import ImageGrab
+import os
 import time
-from PIL import Image
-import numpy as np
 
-# Folder
-folder = "frames"
+# Create a folder to store the screenshot if it doesn't exist
+folder = "screenshots"
+if not os.path.exists(folder):
+    os.makedirs(folder)
 
-# Initialize the webcam
-cap = cv2.VideoCapture(0)
+# Constant filename for the screenshot
+filename = os.path.join(folder, "screenshot.png")
 
-# Check if the webcam is opened correctly
-if not cap.isOpened():
-    raise IOError("Cannot open webcam")
-
-# Wait for the camera to initialize and adjust light levels
-time.sleep(2)
+# Function to take a screenshot
+def take_screenshot(filename):
+    # Capture the entire screen
+    screen = ImageGrab.grab()
+    # Save the image file
+    screen.save(filename)
 
+try:
     while True:
-    ret, frame = cap.read()
-    if ret:
-        # Convert the frame to a PIL image
-        pil_img = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
-
-        # Resize the image
-        max_size = 250
-        ratio = max_size / max(pil_img.size)
-        new_size = tuple([int(x*ratio) for x in pil_img.size])
-        resized_img = pil_img.resize(new_size, Image.LANCZOS)
-
-        # Convert the PIL image back to an OpenCV image
-        frame = cv2.cvtColor(np.array(resized_img), cv2.COLOR_RGB2BGR)
-
-        # Save the frame as an image file
-        print("📸 Say cheese! Saving frame.")
-        path = f"{folder}/frame.jpg"
-        cv2.imwrite(path, frame)
-    else:
-        print("Failed to capture image")
-
-    # Wait for 2 seconds
-    time.sleep(2)
-
-# Release the camera and close all windows
-cap.release()
-cv2.destroyAllWindows()
+        take_screenshot(filename)
+        print(f"Screenshot saved as {filename}")
+        time.sleep(5)  # Wait for 5 seconds before taking the next screenshot
+except KeyboardInterrupt:
+    print("Stopped taking screenshots")

narrator.py

@@ -24,7 +24,8 @@ def encode_image(image_path):
 
 
 def play_audio(text):
-    audio = generate(text=text, voice="ENfvYmv6CRqDodDZTieQ", model="eleven_turbo_v2")
+    // voice param will be your Voice_id coming from the Elevenlabs API
+    audio = generate(text=text, voice="ELEVENLABS_SELECTED_VOICE_ID", model="eleven_turbo_v2")
 
     unique_id = base64.urlsafe_b64encode(os.urandom(30)).decode("utf-8").rstrip("=")
     dir_path = os.path.join("narration", unique_id)
@@ -59,8 +60,7 @@ def analyze_image(base64_image, script):
             {
                 "role": "system",
                 "content": """
-                You are Sir David Attenborough. Narrate the picture of the human as if it is a nature documentary.
-                Make it snarky and funny. Don't repeat yourself. Make it short. If I do anything remotely interesting, make a big deal about it!
+                You are a senior frontend technical lead whos task is to sarcastically review other programmers pure code snippets on screenshots you get. be short, harsh, and very sarcastic. Roast me in 5-8 sentences in the response.
                 """,
             },
         ]
@@ -77,7 +77,7 @@ def main():
 
     while True:
         # path to your image
-        image_path = os.path.join(os.getcwd(), "./frames/frame.jpg")
+        image_path = os.path.join(os.getcwd(), "./screenshots/screenshot.png")
 
         # getting the base64 encoding
         base64_image = encode_image(image_path)