AI900 - Can Speech-to-Text service used with endpoints instead of location?

Jun Kai Herman Teo 61 Reputation points
2021-05-08T06:49:35.453+00:00

Greetings.

I like to ask a question, hopefully not too rudimentary. I am on a learning path for AI900. Ever since I was on the path, I learnt that to deploy the Cognitive Services or any Service, you need the primary key and the endpoint. It was ingrained in my mind ever since, until I reach the module for Speech.

In Speech, for the code to work, I will need to instead key in the primary key and the location (instead of endpoint).

I am a bit confused here, as far as I understand, Speech should also be able to used with endpoint? I surmised the Python code in Github was written to use token, thus a key and location will be needed?

Am I right to say that? Or Speech requires location to be input rather than endpoint?

Thank you!

Kind regards,
Herman

Azure Speech in Foundry Tools
Foundry Tools
Foundry Tools

Formerly known as Azure AI Services or Azure Cognitive Services is a unified collection of prebuilt AI capabilities within the Microsoft Foundry platform

0 comments

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Ramr-msft 17,836 Reputation points
    2021-05-10T09:23:00.94+00:00

    @Jun Kai Herman Teo Thanks for the question. Can you please share the code that you are trying. To call the Speech service using the Speech SDK, you need to create a SpeechConfig.

    There are a few ways that you can initialize a SpeechConfig:

    With an endpoint: pass in a Speech service endpoint. A key or authorization token is optional.
    With a host: pass in a host address. A key or authorization token is optional.
    With an authorization token: pass in an authorization token and the associated region.

    Please follow the quick-start samples.

    Was this answer helpful?

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.