Does Azure have an API for separating sentences with new lines from long Docx documents?

One approach you could consider is using Azure's Text Analytics API, which provides various natural language processing capabilities, including sentence boundary detection.

To use the Text Analytics API to split long text into sentences, you would first need to sign up for an Azure account and set up a Text Analytics resource. Then, you can use the API to send the long text to be analyzed, and the API will return the text with sentences separated by new lines. Here is an example of how you could use the Text Analytics API in Python to split long text into sentences:

import requests  
  
# Replace YOUR_KEY with your Text Analytics API key  
api_key = "YOUR_KEY"  
  
# Set the endpoint URL  
endpoint = "https://<YOUR_RESOURCE_NAME>.cognitiveservices.azure.com/text/analytics/v3.1-preview.3/languages"  
  
# Set the headers  
headers = {  
    "Ocp-Apim-Subscription-Key": api_key  
}  
  
# Set the document  
document = {  
    "documents": [  
        {  
            "id": "1",  
            "text": "This is a long text with multiple sentences. Here is another sentence. And another one. And one more."  
        }  
    ]  
}  
  
# Send the request  
response = requests.post(endpoint, headers=headers, json=document)  
  
# Get the sentences  
sentences = response.json()["documents"][0]["sentences"]  
  
# Print the sentences  
for sentence in sentences:  
    print(sentence["text"])