MovieLife 电影生活
今天看到一个很有意思的项目:https://www.lampysecurity.com/post/the-infinite-audio-book
“我有一个看似愚蠢的想法。通常,这类想法只是一闪而过,很少会付诸实践。但这次有所不同。假如你的生活是一部电影,它会讲述什么故事?会发生什么?我的想法就是从这里开始的。随着 AI 的兴起,我想看看是否可以让 AI 实时讲述我的生活。我们的设想是让相机拍摄一张照片,生成对照片的描述,然后由 ChatGPT 基于所看到的内容写一个叙事场景,再将文本转换为语音并播放。”
我的实现
在整个项目中,我使用了笔记本的摄像头进行操作,运行在笔记本上,感觉非常有趣。ChatGPT的描述充满了正能量!最初的代码无法运行,因此我参考了https://platform.openai.com/docs/guides/vision
,进行了修改,并成功在我的电脑上运行起来。至于树莓派,我了解得不多,正在考虑是否可以在手机上部署,但还没有深入研究。
项目概念
- 创意起源:作者反思了人生如电影的概念,探索了使用AI实时叙述他的人生。
- 技术整合:该项目利用了
OpenAI
的各种服务,包括图像识别、语言模型和文字转语音。
硬件设置
- 选择设备:一个带有Pi相机和Pi Sugar 3电池的Raspberry Pi Zero,以便携带。
- 其他要求:
- 带有micro HDMI的显示器,用于配置。
- 鼠标/键盘进行交互。
- USB micro转female A适配器。
- SD卡用于Raspberry Pi OS。
- 由于缺乏音频插孔,需要无线耳机。
设计和3D打印
- 外壳设计:作者修改了现有的3D外壳设计,以适应电池,并使用Bambu Lab P1S 3D Printer。
软件和API集成
- OpenAI API设置:
- 创建账户并生成API密钥。
- 解释API调用成本和使用情况。
代码实现
-
编程语言:选择Python来编码项目。
-
分步细节:
-
配置文件.env
OPENAI_API_KEY="这里填入你的API_KEY"
-
导入必要的库。
from pathlib import Path from openai import OpenAI import requests import os import cv2 import base64 import time import pygame from dotenv import load_dotenv# 加载 .env 文件 load_dotenv() # OpenAI API key client = OpenAI()# OpenAI API Key api_key = os.getenv("OPENAI_API_KEY") # Path to your image image_path = "vision.jpg"# Getting the base64 string base64_image = "error"headers = {"Content-Type": "application/json","Authorization": f"Bearer {api_key}" }payload = {"model": "gpt-4o-mini","messages": [{"role": "user","content": [{"type": "text","text": "请描述这张图片?"},{"type": "image_url","image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}]}],"max_tokens": 300 }
-
从相机捕获图像。
def capture_webcam_photo(save_directory="webcam_photos"):# Create directory if it doesn't existif not os.path.exists(save_directory):os.makedirs(save_directory)# Open default camera (usually the first camera)cap = cv2.VideoCapture(1)# Capture frame-by-frameret, frame = cap.read()# Generate a unique filenamefilename = os.path.join(save_directory, "webcam_photo.jpg")# Save the captured frame as an imagecv2.imwrite(filename, frame)# Release the capturecap.release()return filename
-
将图像编码为base64格式,以便提交API。
# Function to encode the image def encode_image(image_path):with open(image_path, "rb") as image_file:return base64.b64encode(image_file.read()).decode('utf-8')
-
使用OpenAI的模型根据图像描述生成叙述性响应。
def generate_response(prompt):name = "BoBo"age = "60"location = "体操之乡 湖北仙桃"response = client.chat.completions.create(model="gpt-4o-mini",messages=[{"role": "system","content": "你是一部电影的叙述者,讲述一个名叫 " + name + "。他的年龄 " + age + " ,生活在 " + location + "。当你看到一张场景图片时,你可以从" + name + "的角度描述这张照片,所有人物都用第三人称。 "},{"role": "user", "content": prompt}])return response.choices[0].message.content
-
将文本响应转换为语音并播放。
def text_to_speech(text):speech_file_path = Path(__file__).parent / "speech.mp3"response = client.audio.speech.create(model="tts-1",voice="alloy",input=text)response.stream_to_file(speech_file_path)return speech_file_pathdef play_mp3(file_path):# Initialize Pygamepygame.init()try:# Initialize the mixerpygame.mixer.init()# Load the MP3 filepygame.mixer.music.load(file_path)# Play the MP3 filepygame.mixer.music.play()# Wait until the music finishes playingwhile pygame.mixer.music.get_busy():pygame.time.Clock().tick(10) # Adjust the playback speedexcept pygame.error as e:print(f"Error playing MP3: {e}")finally:# Cleanup Pygamepygame.mixer.music.stop()pygame.mixer.quit()pygame.quit()
主函数:
while True:start_time = time.time()saved_path = capture_webcam_photo()base64_image = encode_image(saved_path)# 将图像插入到 payload 中payload["messages"][0]["content"][1]["image_url"]["url"] = "data:image/jpeg;base64," + base64_image# 发送请求response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)# 检查响应状态if response.status_code != 200:print(f"Error: {response.status_code} - {response.text}")continue # 跳过此次循环,继续尝试jsonZ = response.json()# 检查是否有 'choices' 键if 'choices' in jsonZ and len(jsonZ['choices']) > 0:try:response_text = generate_response(jsonZ["choices"][0]["message"]["content"])output_file = text_to_speech(response_text) # play_mp3(output_file) # except KeyError as e:print(f"KeyError: {e}")print("Received response:", jsonZ)continue # 跳过此循环并记录错误else:print("No choices found in response")# 计算经过的时间elapsed_time = time.time() - start_time# 等待剩余时间remaining_time = max(0, 20 - int(elapsed_time))time.sleep(remaining_time)
-
主要功能
- 连续运行:主循环每20秒捕获一次图像,通过
OpenAI API
进行处理,生成叙述,转换为语音,并播放。
完整代码
'''
@File : movielife
@Author : Bobo
@Blog : https://blog.csdn.net/chinagaobo
@Note : This code is for learning and communication purposes only
'''from pathlib import Path
from openai import OpenAI
import requests
import os
import cv2
import base64
import time
import pygame
from dotenv import load_dotenv# 加载 .env 文件
load_dotenv()
# OpenAI API key
client = OpenAI()# OpenAI API Key
api_key = os.getenv("OPENAI_API_KEY")
# Path to your image
image_path = "vision.jpg"# Getting the base64 string
base64_image = "error"headers = {"Content-Type": "application/json","Authorization": f"Bearer {api_key}"
}payload = {"model": "gpt-4o-mini","messages": [{"role": "user","content": [{"type": "text","text": "请描述这张图片?"},{"type": "image_url","image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}]}],"max_tokens": 300
}# Function to encode the image
def encode_image(image_path):with open(image_path, "rb") as image_file:return base64.b64encode(image_file.read()).decode('utf-8')def generate_response(prompt):name = "BoBo"age = "60"location = "体操之乡 湖北仙桃"response = client.chat.completions.create(model="gpt-4o-mini",messages=[{"role": "system","content": "你是一部电影的叙述者,讲述一个名叫 " + name + "。他的年龄 " + age + " ,生活在 " + location + "。当你看到一张场景图片时,你可以从" + name + "的角度描述这张照片,所有人物都用第三人称。 "},{"role": "user", "content": prompt}])return response.choices[0].message.contentdef text_to_speech(text):speech_file_path = Path(__file__).parent / "speech.mp3"response = client.audio.speech.create(model="tts-1",voice="alloy",input=text)response.stream_to_file(speech_file_path)return speech_file_pathdef capture_webcam_photo(save_directory="webcam_photos"):# Create directory if it doesn't existif not os.path.exists(save_directory):os.makedirs(save_directory)# Open default camera (usually the first camera)cap = cv2.VideoCapture(0) # 使用内置摄像头# Capture frame-by-frameret, frame = cap.read()# Generate a unique filenamefilename = os.path.join(save_directory, "webcam_photo.jpg")# Save the captured frame as an imagecv2.imwrite(filename, frame)# Release the capturecap.release()return filenamedef play_mp3(file_path):# Initialize Pygamepygame.init()try:# Initialize the mixerpygame.mixer.init()# Load the MP3 filepygame.mixer.music.load(file_path)# Play the MP3 filepygame.mixer.music.play()# Wait until the music finishes playingwhile pygame.mixer.music.get_busy():pygame.time.Clock().tick(10) # Adjust the playback speedexcept pygame.error as e:print(f"Error playing MP3: {e}")finally:# Cleanup Pygamepygame.mixer.music.stop()pygame.mixer.quit()pygame.quit()while True:start_time = time.time()saved_path = capture_webcam_photo()base64_image = encode_image(saved_path)# 将图像插入到 payload 中payload["messages"][0]["content"][1]["image_url"]["url"] = "data:image/jpeg;base64," + base64_image# 发送请求response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)# 检查响应状态if response.status_code != 200:print(f"Error: {response.status_code} - {response.text}")continue # 跳过此次循环,继续尝试jsonZ = response.json()# 检查是否有 'choices' 键if 'choices' in jsonZ and len(jsonZ['choices']) > 0:try:response_text = generate_response(jsonZ["choices"][0]["message"]["content"])output_file = text_to_speech(response_text) # play_mp3(output_file) # except KeyError as e:print(f"KeyError: {e}")print("Received response:", jsonZ)continue # 跳过此循环并记录错误else:print("No choices found in response")# 计算经过的时间elapsed_time = time.time() - start_time# 等待剩余时间remaining_time = max(0, 20 - int(elapsed_time))time.sleep(remaining_time)
实测案例
chatGPT的描述:在这张图片中 Bobo看到一个男子坐在桌前 面带微笑 眼镜反射出柔和的光泽 这个男人的手肘支撑在下巴旁 看起来十分放松 似乎正沉浸在与人交流的愉悦中 Bobo想这样的瞬间很难得 尤其是在压力重重的生活中 室内环境给人一种温馨舒适的感觉 整齐的墙面与那扇门形成一种和谐的背景 似乎在提醒每一个人 生活中依旧有着宁静与安详 Bobo的心情也随之变得轻松起来 彷佛可以感受到这个男子所散发出的友好气息 他觉得在这个快速发展的时代 能有这样一份从容不迫和愉快的交流 是多么美好的事情 或许这就是生活的意义所在。
测试案例