语音服务支持的区域Speech service supported regions

• 09/02/2020
• • 
  • 

通过语音服务，应用程序可将音频转换为文本、执行语音翻译以及将文本转换为语音。The Speech service allows your application to convert audio to text, perform speech translation, and covert text to speech. 多个区域中均提供该服务，这些区域为语音 SDK 和 REST API 使用唯一终结点。The service is available in multiple regions with unique endpoints for the Speech SDK and REST APIs.

此处提供了对所有区域的语音体验执行自定义配置的语音门户： https://speech.azure.cnThe Speech portal to perform custom configurations to your speech experience for all the regions is available here: https://speech.azure.cn

考虑区域时，请注意以下几点：Keep in mind the following points when considering regions:

• 如果应用程序使用语音 SDK，请在创建语音配置时提供区域标识符，例如 chinaeast2。If your application uses a Speech SDK, you provide the region identifier, such as chinaeast2, when creating a speech configuration.
• 如果应用程序使用某个语音服务的 REST API，则区域是你在发出请求时使用的终结点 URI 的一部分。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.
• 为某个区域创建的密钥仅在该区域有效。Keys created for a region are valid only in that region. 尝试在其他区域使用此类密钥会导致身份验证错误。Attempting to use them with other regions will result in authentication errors.

语音 SDKSpeech SDK

在语音 SDK 中，区域指定为字符串（例如，在 C# 语音 SDK 中用作 SpeechConfig.FromSubscription 的参数）。In the Speech SDK, regions are specified as a string (for example, as a parameter to SpeechConfig.FromSubscription in the Speech SDK for C#).

语音转文本、文本转语音和翻译Speech-to-text, text-to-speech, and translation

语音自定义门户在此处提供： https://speech.azure.cnThe speech customization portal is available here: https://speech.azure.cn

可以在以下区域使用语音服务，以进行语音识别、文本转语音和翻译：The Speech service is available in these regions for speech recognition, text-to-speech, and translation:

如果使用语音 SDK，则区域由区域标识符指定（例如，作为 SpeechConfig.FromSubscription 的参数）。If you use the Speech SDK, regions are specified by the Region identifier (for example, as a parameter to SpeechConfig.FromSubscription). 请确保该区域与订阅的区域匹配。Make sure the region is matching the region of your subscription.

意向识别Intent recognition

通过语音 SDK 实现意向识别的可用区域如下：Available regions for intent recognition via the Speech SDK are the following:

这是语言理解服务 (LUIS) 支持的发布区域的子集。This is a subset of the publishing regions supported by the Language Understanding service (LUIS).

REST APIREST APIs

语音服务还为语音转文本和文本转语音请求公开 REST 终结点。The Speech service also exposes REST endpoints for speech-to-text and text-to-speech requests.

语音转文本Speech-to-text

有关语音转文本的参考文档，请参阅语音转文本 REST API。For speech-to-text reference documentation, see Speech-to-text REST API.

REST API 的终结点具有以下格式：The endpoint for the REST API has this format:

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

将 <REGION_IDENTIFIER> 替换为与下表中的订阅区域匹配的标识符：Replace <REGION_IDENTIFIER> with the identifier matching the region of your subscription from this table:

文本转语音Text-to-speech

有关文本转语音的参考文档，请参阅文本转语音 REST API。For text-to-speech reference documentation, see Text-to-speech REST API.

标准语音和神经语音Standard and neural voices

使用下表按区域/终结点确定标准语音和神经语音的可用性：Use this table to determine availability of standard and neural voices by region/endpoint:

自定义语音Custom voices

如果已经创建了自定义语音字体，请使用已创建的终结点。If you've created a custom voice font, use the endpoint that you've created. 还可以使用下面列出的终结点，并将 {deploymentId} 替换为语音模型的部署 ID。You can also use the endpoints listed below, replacing the {deploymentId} with the deployment ID for your voice model.