Azure-docs: Reference of batch transcription API is missing

[strohne]

The docs state that "The Batch transcription API is using a REST service [...] You can use the API from any language. The next section describes how it is used."

The description of endpoints, parameters etc. is completely missing. For example, how do I use the API from Python?

---

Document Details

⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.

• ID: 73fb7e76-fb80-c420-2efe-e3ca3a27b749
• Version Independent ID: 07a42557-deb3-e4b3-3f14-f26a27be49c2
• Content: Azure Batch transcription API
• Content Source: articles/cognitive-services/Speech-Service/batch-transcription.md
• Service: cognitive-services
• GitHub Login: @PanosPeriorellis
• Microsoft Alias: panosper

[YutongTie-MSFT]

@strohne Thanks for the feedback! I have assigned the issue to the content author to investigate further and update the document as appropriate.

@PanosPeriorellis Hi, can you please take a look of this issue? More details are needed in the document, please update the document as necessary. Thanks a lot!

[tchristiani]

@YutongTie-MSFT please reassign to @erhopf

[erhopf]

@wolfma61 - Can you have someone on your team review this issue?

[tchristiani]

@YutongTie-MSFT please reassign to @wolfma61

[wolfma61]

neither author nor owner of this ... @PanosPeriorellis

[tchristiani]

OK, thank you! @YutongTie-MSFT please reassign back to @PanosPeriorellis

[strohne]

You Microsoft people are so funny. :) After 20 days, do we really have a bunch of reactions here, none ist helpful?

I really spent a lot of time to get batch speech recognition working with your REST API. Until now, it doesn't work. The main problems:

• Which of the various endpoints should I use (URL)?
• Where should I register and which of the numerous subscription keys is right?

I uploaded my audio file to a storage container and posted the following body to https://westeurope.cris.ai/api/speechtotext/v2.0/transcriptions:

{
"name":"audiogerman",
"recordingsUrl":"https://facepager.blob.core.windows.net/audio/audio-german.wav",
"locale":"de-DE"
}

The Ocp-Apim-Subscription-Key header is filled with a key from https://westeurope.cris.ai/Subscriptions

I keep getting error 400 InvalidSubscription. Only "Standard" subscriptions for the region of the called service are valid.

BTW: I created a question on stackoverflow as well: https://stackoverflow.com/questions/52932413/batch-transcription-with-microsoft-azure-rest-api/53008994

Maybe you could help out?

[rarera]

Hi Strohne,

I am very sorry for your experience.
The problem is that the Batch Transcription API, does not support a free key yet.
You need to have a SpeechServices.S0 key for this.
This should have been stated in the documentation, I will create a bug for the author, to add this information to the documentation.

Sorry for your inconveniences,
Ramin

[strohne]

Thanks for your reply. Where do I get such a key?

[rarera]

Hi Strohne,

portal.azure.com -> + Create a resource (top left of the screen) -> Now search for and select "Speech" -> Create -> here select the correct data center, and select S0 as pricing tier.

From the created resource you can then get the Key.

Ok hope this helps,
Ramin

[rarera]

Hi @PanosPeriorellis ,

can you please merge my PRs to this document and we also need a page with screenshots showing how to get a proper subscription key.

Thanks,
Ramin

[strohne]

great it works, thank you!

[YutongTie-MSFT]

@strohne
We will now proceed to close this thread. If there are further questions regarding this matter, please respond here and @YutongTie-MSFT and we will gladly continue the discussion.