This article assumes that your organization contains published Architect flows that use Enhanced TTS with Microsoft Azure, and describes how to migrate your existing flows to use the TTS engine from the Microsoft Azure Cognitive Services TTS integration as a BYOT model.

This article applies to you if you are using Enhanced TTS with Microsoft Azure in the following flows:

• Call flows
• Secure flows
• In-queue flows
• Bot flows

Before you begin

Review the following articles:

• Text-to-speech (TTS) engines overview
• About text-to-speech (TTS) engines
• About bring your own technology (BYOT)
• Bring your own technology services model–per turn/minute rates (current model)

Install the Microsoft Azure Cognitive Services TTS integration

Install, configure, and activate the Microsoft Azure Cognitive Services TTS integration.

1. Install the Microsoft Azure Cognitive Services TTS integration.
2. Activate and configure the Microsoft Azure TTS integration.

Select the Microsoft Azure Cognitive Services TTS engine and voice for a flow

1. From the Architect home page, click the Dependency Search tab.
2. From the Select a dependency type list, choose the appropriate Text To Speech engine.
3. From the Select an engine list, choose the appropriate engine.
4. To open a flow from the list of search results, click the flow name.
5. Under Settings, click Supported Languages.
6. Locate the existing supported language.
7. In the Text To Speech column for the supported language, do the following:
   1. Under Engine, select the TTS engine for the flow:
      • Microsoft Azure Cognitive Services TTS: Select this option to use the Microsoft Azure TTS integration.
   2. Under Voice, select the voice you want to read the text to speech.
      Note: You can select any voice that the selected TTS engine supports. The TTS voice does not need to match the flow’s language. For example, you can use a language as your flow’s default language for which Architect supports speech recognition (“en-GB”), and at the same time, use a different TTS voice (“en-IE”) to meet your customers’ language needs.
8. Save and publish the flow.

Test your TTS engine playback

For information on testing your TTS engine voice in a flow, see Test your TTS engine playback.