main.py

from IPython.display import display, Image, Audio

import cv2  # We're using OpenCV to read video, to install !pip install opencv-python
import base64
import time
from openai import (
    OpenAI,
)  # We're using OpenAI to create transaltion, to install !pip install openai
import os
import requests  # install !pip install requests

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

# Using GPT's visual capabilities to get a description of a video
video = cv2.VideoCapture("data/bison.mp4")

base64Frames = []
while video.isOpened():
    success, frame = video.read()
    if not success:
        break
    _, buffer = cv2.imencode(".jpg", frame)
    base64Frames.append(base64.b64encode(buffer).decode("utf-8"))

video.release()
print(len(base64Frames), "frames read.")


PROMPT_MESSAGES = [
    {
        "role": "user",
        "content": [
            "These are frames from a video that I want to upload. Generate a compelling description that I can upload along with the video.",
            *map(lambda x: {"image": x, "resize": 768}, base64Frames[0::50]),
        ],
    },
]
params = {
    "model": "gpt-4o",
    "messages": PROMPT_MESSAGES,
    "max_tokens": 200,
}

result = client.chat.completions.create(**params)
print(result.choices[0].message.content)

PROMPT_MESSAGES = [
    {
        "role": "user",
        "content": [
            "These are frames of a video. Create a short voiceover script in the style of David Attenborough. Only include the narration.",
            *map(lambda x: {"image": x, "resize": 768}, base64Frames[0::60]),
        ],
    },
]
params = {
    "model": "gpt-4o",
    "messages": PROMPT_MESSAGES,
    "max_tokens": 500,
}

result = client.chat.completions.create(**params)
print(result.choices[0].message.content)

response = requests.post(
    "https://api.openai.com/v1/audio/speech",
    headers={
        "Authorization": f"Bearer {os.environ['OPENAI_API_KEY']}",
    },
    json={
        "model": "tts-1-1106",
        "input": result.choices[0].message.content,
        "voice": "onyx",
    },
)

audio = b""
for chunk in response.iter_content(chunk_size=1024 * 1024):
    audio += chunk
Audio(audio)


# Save the audio to a file
with open("generated_audio.mp3", "wb") as f:
    f.write(audio)

print("Audio saved as 'generated_audio.mp3'")