Foxleads564

-->

The Speech service allows your application to convert audio to text, perform speech translation, and covert text to speech. The service is available in multiple regions with unique endpoints for the Speech SDK and REST APIs.

1. With Speech Central you can take the web on the go. Listen to the headlines from your favorite sites and select their linked articles to be read by using only the headphones or Bluetooth hands-free. For the first time feel the freedom without the need to prepare your text to speech session in advance.
2. App Store Description With over 10,000 licenses sold and consistent ratings above 4 stars Speech Central is one of the leading global text-to-speech brands. It was nominated for the best iOS.

The Speech portal to perform custom configurations to your speech experience for all the regions is available here: https://speech.microsoft.com

Speech 151 students can find more examples of specific purpose statements and central ideas on pages of 240-251 of our text. You can also find examples of Main Points. The Public Speakers' Resources.

Keep in mind the following points when considering regions:

• If your application uses a Speech SDK, you provide the region identifier, such as westus, when creating a speech configuration.
• If your application uses one of the Speech service's REST APIs, the region is part of the endpoint URI you use when making requests.
• Keys created for a region are valid only in that region. Attempting to use them with other regions will result in authentication errors.

Speech SDK

In the Speech SDK, regions are specified as a string(for example, as a parameter to SpeechConfig.FromSubscription in the Speech SDK for C#).

Speech-to-text, text-to-speech, and translation

The speech customization portal is available here: https://speech.microsoft.com

The Speech service is available in these regions for speech recognition, text-to-speech, and translation:

If you use the Speech SDK, regions are specified by the Region identifier (for example, as a parameter to SpeechConfig.FromSubscription). Make sure the region is matching the region of your subscription.

If you plan to train a custom model with audio data, use one of the regions with dedicated hardware for faster training. You can use the REST API to copy the fully trained model to another region later.

Intent recognition

Available regions for intent recognition via the Speech SDK are the following:

This is a subset of the publishing regions supported by the Language Understanding service (LUIS).

Speech Central Lite

Voice assistants

The Speech SDK supports voice assistant capabilities through Direct Line Speech in these regions:

Speaker Recognition

Speaker Recognition is currently only available in the westus region.

REST APIs

The Speech service also exposes REST endpoints for speech-to-text and text-to-speech requests.

Speech-to-text

For speech-to-text reference documentation, see Speech-to-text REST API.

The endpoint for the REST API has this format:

Speech Central Idea

Replace <REGION_IDENTIFIER> with the identifier matching the region of your subscription from this table:

Note

The language parameter must be appended to the URL to avoid receiving an 4xx HTTP error. For example, the language set to US English using the West US endpoint is: https://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US.

Text-to-speech

For text-to-speech reference documentation, see Text-to-speech REST API.

Neural and standard voices

Use this table to determine availability of neural and standard voices by region/endpoint:

Tip

Voices in preview are only available in these 3 regions: East US, West Europe and Southeast Asia.

Custom voices

If you've created a custom voice font, use the endpoint that you've created. You can also use the endpoints listed below, replacing the {deploymentId} with the deployment ID for your voice model.

Custom Neural Voice

The following table details regional support for Custom Neural Voice features.

Long audio API

Speech Central For Mac

The Long audio API is available in multiple regions with unique endpoints.

Speech Central Idea