How can I use Azure to create a more reliable version of Microsoft Translator App?

Lauren K 0 Reputation points
2025-09-15T03:15:40.29+00:00

I’m an 8th grade teacher in NYC. This week two new students arrived and do not speak any English. Our school does not have an ELL teacher in content classes and I’m struggling to support them. I found the Microsoft Translator App and it was perfect! I love that it shows both the English and Spanish/Arabic and that it saves the transcription so they can refer back to it. The issue is during peak daytime hours, it doesn’t work consistently and says “a conversation cannot be started.”

A google search suggested Azure. The agent suggested I purchase the Pay as you Go plan and that the Microsoft Translator App runs on the Azure Cognitive AI Translator and that I would get a similar experience. I signed up but when I logged in, it is MUCH more technical than I expected and I have no idea what to do next.

My goal is to get the same Microsoft Translator experience with better reliability. I would greatly appreciate any HELP!!! Thank you

Azure AI Translator
Azure AI Translator
An Azure service to easily conduct machine translation with a simple REST API call.
{count} votes

2 answers

Sort by: Most helpful
  1. SRILAKSHMI C 8,295 Reputation points Microsoft External Staff Moderator
    2025-09-15T06:05:50.7733333+00:00

    Hello Lauren K,

    Welcome to Microsoft Q&A and Thank you for reaching out.

    I understand that you’re looking to create a more reliable version of the Microsoft Translator App using Azure, and you’re feeling a bit overwhelmed by the technical side. The important thing to know is that the Microsoft Translator App itself runs on the same Azure Cognitive Services Translator service.

    The difference is that the free app uses a shared service, which can slow down or stop working during busy hours. By creating your own Translator resource in Azure, you get dedicated capacity, which means it will be much more reliable for your students.

    To get started, you’ll need to create a Translator resource in the Azure Portal. Once you log in, click on “Create a resource” and search for “Translator.” From there, choose the Pay-As-You-Go plan (which you already have), pick a region close to you for example, “East US” works best in NYC and then click “Review + Create.” When the resource is ready, you’ll be able to see two keys and an endpoint URL. Think of these as your personal access codes for the Translator service.

    Follow the instructions found in this quickstart guide for setting it up, which includes generating the necessary key and endpoint to connect to the service.

    After setting up the resource, you may want to explore the Custom Translator feature. This is especially useful in a classroom setting because it lets you fine-tune translations for specific subjects. For example, if you’re teaching math or science, you can train the service to handle technical terms more accurately, so your students see better translations.

    The Azure Translator works through something called an API, this API overview which is just a way for apps to talk to each other. At first this might sound technical, but Microsoft provides step-by-step quickstarts and example projects that you can use without needing deep coding knowledge. These show how to translate text or speech using your Translator key and endpoint, so you can get set up quickly.

    If your main concern is helping students in real time, Azure also has great options for live translation. You can use the Speech SDK to turn spoken English into real-time subtitles in Spanish or Arabic. If your school uses Microsoft Teams, you can also enable live captions and translation during classes. This can be a very practical way for students to follow along while you’re teaching.

    Finally, don’t be discouraged if your first setup isn’t perfect. Test the tool with your students, see what works best, and adjust as needed. Over time, you can refine translations using Custom Translator to make them more accurate and tailored for your classroom. The key advantage is that your Azure Translator resource gives you dedicated reliability, so your students won’t run into the “conversation cannot be started” error during peak hours.

    I Hope this helps. Do let me know if you have any further queries.


    If this answers your query, please do click Accept Answer and Yes for was this answer helpful.

    Thank you!

    0 comments No comments

  2. Sina Salam 25,841 Reputation points Volunteer Moderator
    2025-09-22T17:11:56.6666667+00:00

    Hello Lauren K,

    Welcome to the Microsoft Q&A and thank you for posting your questions here.

    Regarding your need and questions, the options and straight solution you can do are the followings:

    1. Use PowerPoint Live Subtitles or Teams live translated captions so your new students (participants) can follow along and you can download transcripts afterwards (Fast, reliable. and no code). - https://support.microsoft.com/en-us/office/present-with-real-time-automatic-captions-or-subtitles-in-powerpoint-68d20e49-aec3-456a-939d-34a79e8ddd5f
    2. Ask IT to create a small Azure Translator and Speech resource in East US and configure a Power Automate flow that will let you record/submit classroom audio and automatically save transcripts + translations to SharePoint (low-code). - https://free.blessedness.top/en-us/azure/ai-services/translator/how-to/create-translator-resource
    3. Get a developer or IT to implement the Speech SDK + Translator REST pipeline. This will reproduce the Microsoft Translator App behavior but on your own Azure resources for better reliability and saved transcripts. - https://free.blessedness.top/en-us/azure/storage/blobs/storage-quickstart-blobs-nodejs

    I hope this is helpful! Do not hesitate to let me know if you have any other questions or clarifications.


    Please don't forget to close up the thread here by upvoting and accept it as an answer if it is helpful.

    0 comments No comments

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.