إطلاق العنان للذكاء الاصطناعي: صياغة روايات الحياة البرية الجذابة باستخدام GPT وواجهة TTS API

from IPython.display import display, Image
import cv2
import base64
 
# Read the video file
video = cv2.VideoCapture("data/bison.mp4")
base64Frames = []
 
# Extract frames
while video.isOpened():
    success, frame = video.read()
    if not success:
        break
    _, buffer = cv2.imencode(".jpeg", frame)
    base64Frames.append(base64.b64encode(buffer).decode("utf-8"))
 
video.release()
print(len(base64Frames), "frames read.")

from IPython.display import display
 
display_handle = display(None, display_id=True)
for img in base64Frames:
    display_handle.update(Image(data=base64.b64decode(img.encode("utf-8"))))
    time.sleep(0.025)

from openai import OpenAI
import os
 
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY", ""))
 
# Prepare prompt messages
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])
        ],
    }
]
 
# Define request parameters
params = {
    "model": "gpt-4",
    "messages": PROMPT_MESSAGES,
    "max_tokens": 200,
}
 
# Get description from GPT-4
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])
        ],
    }
]
 
# Request GPT-4 to create the script
params = {
    "model": "gpt-4",
    "messages": PROMPT_MESSAGES,
    "max_tokens": 500,
}
 
result = client.chat.completions.create(**params)
print(result.choices[0].message.content)

import requests
 
# Request to TTS API
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",
    },
)
 
# Fetch the audio
audio = b""
for chunk in response.iter_content(chunk_size=1024 * 1024):
    audio += chunk
 
# Display audio output
from IPython.display import Audio
 
Audio(audio)