Speech service supported regions

The Speech service allows your application to convert audio to text, perform speech translation, and convert text to speech. The service is available in multiple regions with unique endpoints for the Speech SDK and REST APIs. You can perform custom configurations to your speech experience, for all regions, at the Speech Studio.

Keep in mind the following points:

  • If your application uses a Speech SDK, you provide the region identifier, such as chinaeast2, when you create a SpeechConfig. Make sure the region matches the region of your subscription.
  • If your application uses one of the Speech service 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. If you attempt to use them with other regions, you get authentication errors.

Note

Speech service doesn't store or process customer data outside the region the customer deploys the service instance in.

Speech service

The following regions are supported for Speech service features such as speech to text, text to speech, pronunciation assessment, and translation.

Geography Region Region identifier
China China East 2 chinaeast2
China China North 2 chinanorth2
China China North 3 chinanorth3

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 to another region.

REST APIs

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

Speech-to-text

The endpoint for the REST API has this format:

https://<REGION_IDENTIFIER>.stt.speech.azure.cn/speech/recognition/conversation/cognitiveservices/v1

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

Geography Region Region identifier
China China East 2 chinaeast2
China China North 2 chinanorth2
China China North 3 chinanorth3

Note

The language parameter must be appended to the URL to avoid receiving an HTTP error. For example, the language set to US English by using the China East 2 endpoint is: https://chinaeast2.stt.speech.azure.cn/speech/recognition/conversation/cognitiveservices/v1?language=en-US.

For more information, see the speech-to-text REST API.

Text-to-speech

For more information, see the text-to-speech REST API.

Prebuilt neural voices

Use this table to determine availability of neural voices by region or endpoint:

Region Endpoint
China East 2 https://chinaeast2.tts.speech.azure.cn/cognitiveservices/v1
China North 2 https://chinanorth2.tts.speech.azure.cn/cognitiveservices/v1
China North 3 https://chinanorth3.tts.speech.azure.cn/cognitiveservices/v1