Speech Engines for Anywhere365
Note: Different Speech Engines can only be used in combination with plugins, for example Dialogue Studio.
Introduction
There are multiple TextToSpeech engines that are currently available, only one SpeechProvider can be selected per UCC A Unified Contact Center, or UCC, is a queue of interactions (voice, email, IM, etc.) that are handled by Agents. Each UCC has its own settings, IVR menus and Agents. Agents can belong to one or several UCCs and can have multiple skills (competencies). An UCC can be visualized as a contact center “micro service”. Customers can utilize one UCC (e.g. a global helpdesk), a few UCC’s (e.g. for each department or regional office) or hundreds of UCC’s (e.g. for each bed at a hospital). They are interconnected and can all be managed from one central location..
Each SpeechProvider can be configured with a SpeechPreferredVoiceName,
When you do not configure the SpeechPreferredVoiceName the UCC will look for an available voice based on the Culture configured in GlobalSettings.
When a speech provider can't initialize or is misconfigured the MicrosoftSpeechSythesizer will be used as fallback.
MicrosoftSpeechSynthesizer
The standard option this is the on-premises text to speech solution, using the Microsoft Speech Sythesizer with the installed voices on the Anywhere365 UCC server.
Setting |
Value |
---|---|
SpeechProvider |
MicrosoftSpeechSynthesizer |
SpeechPreferredVoiceName |
Exampled: Microsoft Server Speech Text to Speech Voice (en-GB, Hazel) |
MicrosoftCognitiveServices
This speech provider uses the Azure cloud service* to generate text to speech audio files. This one offers better quality than the standard Microsoft Speech installed on the UCC server.
* Text to Speech is subject to additional costs and are billed on the used Azure subscription. For rates see https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/ .
A Cognitive Services key can be obtained through the Azure Portal. Just add a "Cognitive Services" resource to your Azure Subscription and copy key 1 from the "Keys and Endpoint" section. Make sure to use correct endpoint addresses in the settings below when you choose to host the service in another region than westeurope.
Setting |
Description |
Value |
---|---|---|
SpeechMicrosoftCognitiveApiKey |
The api key for Microsoft Cognitive services. |
|
SpeechMicrosoftCognitiveApiEndpoint |
The api endpoint for Microsoft Cognitive services. |
Example: https://westeurope.tts.speech.microsoft.com/cognitiveservices/v1 |
SpeechMicrosoftCognitiveApiAuthorizationEndpoint |
The authorization endpoint for Microsoft Cognitive services. |
Example: https://westeurope.api.cognitive.microsoft.com/sts/v1.0/issueToken |
SpeechProvider |
MicrosoftCognitiveServices |
|
SpeechPreferredVoiceName |
Example: Microsoft Server Speech Text to Speech Voice (en-US, JessaNeural) |
GoogleCloudTextToSpeech
Google Cloud Text to Speech service is the one that offers the most comprehensive set of voices, a list of this you can find at https://cloud.google.com/text-to-speech/docs/voices.
For more information about their offering you can have a look here: https://cloud.google.com/speech-to-text
For this plugin you have to configure two lists, GlobalSettings and the PluginSettings lis.
In the PluginSettings list you have to put in the Credentials Json from the Google service.
GlobalSettings
Setting |
Value |
---|---|
SpeechProvider |
GoogleCloudTextToSpeechV1 |
SpeechPreferredVoiceName |
Example: nl-NL-Wavenet-C |
PluginSettings
Setting |
Scope |
Value |
---|---|---|
GoogleAppCredentialsJson |
TextToSpeech |
Json generation in Google Cloud. |