五个 AI API 可自动解决你的日常问题

# AI Image Generation
# pip install requests
import requests
import base64
def generate_image(access_token, prompt):
    url = "https://api.getimg.ai/v1/stable-diffusion/text-to-image"
    headers = {"Authorization": "Bearer {}".format(access_token)}
    data = {
            "model": "stable-diffusion-v1-5",
            "prompt": prompt,
            "negative_prompt": "Disfigured, cartoon, blurry",
            "width": 512,
            "height": 512,
            "steps": 25,
            "guidance": 7.5,
            "seed": 42,
            "scheduler": "dpmsolver++",
            "output_format": "jpeg",
        }
    response = requests.post(url, headers=headers, data=data)
    image_string = response.content
    image_bytes = base64.decodebytes(image_string)
    with open("AI_Image.jpeg", "wb") as f:
        f.write(image_bytes)
if __name__ == "__main__":
    api_key = "YOUR_API_KEY"
    prompt = "a photo of a cat dressed as a pirate"
    image_bytes = generate_image(api_key, prompt)

# AI Proofreading
# pip install requests
import requests
def Proofreader(text):
    api_key = "YOUR_API_KEY"
    url = 'https://api.sapling.ai/api/v1/edits'
    data = {
        'key': api_key,
        'text': text,
        'session_id': 'Test Document UUID',
        'advanced_edits': {
            'advanced_edits': True,
        },
    }
    response = requests.post(url, json=data)
    resp_json = response.json()
    edits = resp_json['edits']
    print("Corrections: ", edits)
if __name__ == '__main__':
    Proofreader("I are going to the store, She don't likes pizza")

# AI Text to Speech
# pip install google-cloud-texttospeech
# pip install playsound
import io
import os
from google.cloud import texttospeech
import playsound
# Set the path to your credentials JSON file
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "credentials.json"
def Text_to_Speech(text):
    client = texttospeech.TextToSpeechClient()
    # Set the language code and the voice name.
    language_code = "en-US"
    voice_name = "en-US-Wavenet-A"
    # Create a request to synthesize speech.
    r = texttospeech.types.SynthesizeSpeechRequest()
    r.text = text
    r.voice = texttospeech.types.VoiceSelectionParams(
        language_code=language_code, name=voice_name)
    # Set the audio encoding.
    r.audio_encoding = texttospeech.types.AudioEncoding.MP3
    # Get the response from the API.
    response = client.synthesize_speech(r)
    # Save the audio to a file.
    with io.open("audio.mp3", "wb") as f:
        f.write(response.audio_content)
    # Play the audio.
    playsound.playsound("audio.mp3", True)
if __name__ == "__main__":
    text = input("Enter the text: ")
    Text_to_Speech(text)

# ChatGPT AI
# pip install openai
import os
import openai
def ask(prompt):
  response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[
      {
        "role": "user",
        "content": prompt
      }
    ],
    temperature=1,
    max_tokens=256,
    top_p=1,
    frequency_penalty=0,
    presence_penalty=0
  )


  print("Ans: ", response)
if __name__ == "__main__":
    ask("Python or JavaScript?")

# AI OCR
# pip install google-cloud-vision
from google.cloud import vision
from google.cloud.vision import types
import os
# Set the path to your credentials JSON file
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "credentials.json"
def OCR(img_path):
    client = vision.ImageAnnotatorClient()
    with open(img_path, 'rb') as image_file:
        content = image_file.read()
    image = types.Image(content=content)
    response = client.text_detection(image=image)
    texts = response.text_annotations
    if texts:
        return texts[0].description
    else:
        return "No text found in the image."
if __name__ == "__main__":
    image_path = "photo.jpg"
    print(OCR(image_path))