Merge pull request #249789 from sally-baolian/patch-148

Update how-to-deploy-and-use-endpoint.md

Author: prmerger-automator[bot]

articles/ai-services/speech-service/how-to-deploy-and-use-endpoint.md

@@ -33,6 +33,10 @@ To create a custom neural voice endpoint:
 1. Select **Custom Voice** > Your project name > **Deploy model** > **Deploy model**. 
 1. Select a voice model that you want to associate with this endpoint.  
 1. Enter a **Name** and **Description** for your custom endpoint.
+1. Select **Endpoint type** according to your scenario. If your resource is in a supported region, the default setting for the endpoint type is *High performance*. Otherwise, if the resource is in an unsupported region, the only available option is *Fast resume*.
+   - *High performance*: Optimized for scenarios with real-time and high-volume synthesis requests, such as conversational AI, call-center bots. It takes around 5 minutes to deploy or resume an endpoint. For information about regions where the *High performance* endpoint type is supported, see the footnotes in the [regions](regions.md#speech-service) table. 
+   - *Fast resume*: Optimized for audio content creation scenarios with less frequent synthesis requests. Easy and quick to deploy or resume an endpoint in under a minute. The *Fast resume* endpoint type is supported in all [regions](regions.md#speech-service) where text to speech is available.
+   
 1. Select **Deploy** to create your endpoint.
 
 After your endpoint is deployed, the endpoint name appears as a link. Select the link to display information specific to your endpoint, such as the endpoint key, endpoint URL, and sample code. When the status of the deployment is **Succeeded**, the endpoint is ready for use.

articles/ai-services/speech-service/regions.md

@@ -34,31 +34,31 @@ The following regions are supported for Speech service features such as speech t
 | ----- | ----- | ----- |
 | Africa | South Africa North | `southafricanorth` <sup>6</sup>|
 | Asia Pacific | East Asia | `eastasia` <sup>5</sup>|
-| Asia Pacific | Southeast Asia | `southeastasia` <sup>1,2,3,4,5</sup>|
-| Asia Pacific | Australia East | `australiaeast` <sup>1,2,3,4</sup>|
+| Asia Pacific | Southeast Asia | `southeastasia` <sup>1,2,3,4,5,7</sup>|
+| Asia Pacific | Australia East | `australiaeast` <sup>1,2,3,4,7</sup>|
 | Asia Pacific | Central India | `centralindia` <sup>1,2,3,4,5</sup>|
 | Asia Pacific | Japan East | `japaneast` <sup>2,5</sup>|
 | Asia Pacific | Japan West | `japanwest` |
 | Asia Pacific | Korea Central | `koreacentral` <sup>2</sup>|
 | Canada | Canada Central | `canadacentral` <sup>1</sup>|
-| Europe | North Europe | `northeurope` <sup>1,2,4,5</sup>|
-| Europe | West Europe | `westeurope` <sup>1,2,3,4,5</sup>|
+| Europe | North Europe | `northeurope` <sup>1,2,4,5,7</sup>|
+| Europe | West Europe | `westeurope` <sup>1,2,3,4,5,7</sup>|
 | Europe | France Central | `francecentral` |
 | Europe | Germany West Central | `germanywestcentral` |
 | Europe | Norway East | `norwayeast` |
 | Europe | Switzerland North | `switzerlandnorth` <sup>6</sup>|
 | Europe | Switzerland West | `switzerlandwest` |
-| Europe | UK South | `uksouth` <sup>1,2,3,4</sup>|
+| Europe | UK South | `uksouth` <sup>1,2,3,4,7</sup>|
 | Middle East | UAE North | `uaenorth` <sup>6</sup>|
 | South America | Brazil South | `brazilsouth` <sup>6</sup>|
 | US | Central US | `centralus` |
-| US | East US | `eastus` <sup>1,2,3,4,5</sup>|
+| US | East US | `eastus` <sup>1,2,3,4,5,7</sup>|
 | US | East US 2 | `eastus2` <sup>1,2,4,5</sup>|
 | US | North Central US | `northcentralus` <sup>4,6</sup>|
-| US | South Central US | `southcentralus` <sup>1,2,3,4,5,6</sup>|
+| US | South Central US | `southcentralus` <sup>1,2,3,4,5,6,7</sup>|
 | US | West Central US | `westcentralus` <sup>5</sup>|
 | US | West US | `westus` <sup>2,5</sup>|
-| US | West US 2 | `westus2` <sup>1,2,4,5</sup>|
+| US | West US 2 | `westus2` <sup>1,2,4,5,7</sup>|
 | US | West US 3 | `westus3` |
 
 <sup>1</sup> The region has dedicated hardware for Custom Speech training. If you plan to train a custom model with audio data, use one of the regions with dedicated hardware for faster training. Then you can [copy the trained model](how-to-custom-speech-train-model.md#copy-a-model) to another region.
@@ -73,6 +73,8 @@ The following regions are supported for Speech service features such as speech t
 
 <sup>6</sup> The region does not support Speaker Recognition.
 
+<sup>7</sup> The region supports the [high performance](how-to-deploy-and-use-endpoint.md#add-a-deployment-endpoint) endpoint type for Custom Neural Voice.
+
 ## Intent recognition
 
 Available regions for intent recognition via the Speech SDK are in the following table.