This article will cover the following.
- Brief Concepts and Prerequisites
- Implementation – Create a new Translator Speech API
- Implementation – Access the Translator Speech API
Translator Speech API
Microsoft Translator Speech API is a cloud-based automatic translation service. The API enables developers to add end-to-end, real-time, speech translations to their applications or services.
Extend the reach of your applications
Across mobile, desktop, and web applications, easily power translation to and from ten languages through the open REST interface of Translator Speech API, a cloud-based automatic speech translation service (also known as machine translation).
Transcribe and translate real-life conversation
Add speech translation to your app, using a technology optimized for translation of real-life conversation.
Adapt to your application needs
Depending on your unique scenarios, use one or more of the available outputs from the API: partial transcriptions as you speak, partial text translations, final transcriptions, final text translation, or audio text-to-speech translation.
Pre-requisites:
Read the following article to create an Azure account for some basic information about Azure to get started.
Implementation – Create a new Translator Speech API
Steps to be followed
- Open the Azure portal and click on Add. Choose category “AI + Cognitive Services” and then select the option of “Translator Speech API”.
- Fill in the details, create a new resource-group, and click on “Create”.
- Go to the “All resources” section and see the newly created “Translator Speech API” named as “translator-speech-api-10-10”.
- Open the Translator Speech API there and see the different options available.
Implementation – Access the Translator Speech API
Steps to be followed -
- In the opened section of the Translator Speech API, click on the “Quick start" menu item.
- Click “Grab Keys” and copy and paste the “KEY-1” into the Notepad file from here.
- Then, go to “Make an API call” and click on the Translator Speech API reference.
- Then, follow the steps there at the reference page. First, generate an “access token” using the key.
- Then, click on Send and copy the access token received in the response.
- Now, query the language sources available for text to speech and choose the scope as “text” to see the list of available languages.
- Click on Send and see the response with the following details.
Happy Learning!