Upload 2 files

gpt4v.py

@@ -0,0 +1,47 @@
+import base64
+from openai import OpenAI
+
+
+class GPT4Vision:
+    def __init__(self):
+        self.client = OpenAI()
+
+    def encode_image(self, image_path):
+        """
+        Encode the image to base64 format.
+
+        :param image_path: Path to the image file.
+        :return: Base64 encoded string of the image.
+        """
+        with open(image_path, "rb") as image_file:
+            return base64.b64encode(image_file.read()).decode('utf-8')
+
+    def describe(self, image_path, user_message):
+        """
+        Get a description of the image using OpenAI's GPT-4 Vision API.
+
+        :param image_path: Path to the image file.
+        :param user_message: Custom text message to send as user input.
+        :return: The API response.
+        """
+        base64_image = self.encode_image(image_path)
+
+        response = self.client.chat.completions.create(
+            model="gpt-4-vision-preview",
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": user_message},
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": f"data:image/png;base64,{base64_image}"
+                            },
+                        },
+                    ],
+                }
+            ],
+            max_tokens=1000,
+        )
+        return response.choices[0]

gpttts.py

@@ -0,0 +1,47 @@
+from pathlib import Path
+from openai import OpenAI
+
+class GPTTTS:
+    def __init__(self, client):
+        self.client = client
+
+    def generate_speech(self, text="No text", model="tts-1-hd", voice="alloy"):
+        """
+        Generate speech from text using OpenAI's text-to-speech API.
+
+        :param text: The text to convert to speech. Defaults to "No text".
+        :param model: The TTS model to use. Defaults to "tts-1-hd".
+        :param voice: The voice to use. Defaults to "alloy".
+        :return: Path to the generated speech file.
+        """
+        # Set default values if parameters are empty
+        model = model if model else "tts-1-hd"
+        voice = voice if voice else "alloy"
+
+        # Create the speech file path
+        speech_file_path = Path(__file__).parent / "speech.mp3"
+
+        # Generate the speech
+        response = self.client.audio.speech.create(
+            model=model,
+            voice=voice,
+            input=text
+        )
+
+        # Save the speech to a file
+        response.stream_to_file(speech_file_path)
+
+        return speech_file_path
+
+# Example usage
+if __name__ == "__main__":
+    client = OpenAI()  # Initialize the OpenAI client
+    tts = GPTTTS(client)
+
+    # Generate speech
+    file_path = tts.generate_speech(
+        text="Today is a wonderful day to build something people love!",
+        model="tts-1-hd",
+        voice="alloy"
+    )
+    print(f"Speech generated at: {file_path}")