About text-to-speech (TTS) engines

AI-generated summary

Genesys Cloud provides comprehensive text-to-speech (TTS) functionality through multiple engine options, including a default Genesys TTS engine and third-party integrations available via the Genesys AppFoundry. The platform supports Genesys Enhanced TTS (an optional, PCI-DSS compliant engine with usage-based billing), Genesys Generative TTS (delivering more natural, human-like speech), and third-party providers including Amazon Polly, Acapela Voice, Google Cloud Text-to-Speech, Microsoft Azure Cognitive Services TTS, Nuance Text-to-Speech, and Speech Morphing. Users can configure TTS engines for use in voice and bot flows, selecting from available voice options and managing language support within Architect. Key technical constraints include a maximum TTS request length of 3, incompatibility between custom TTS voices and Google Cloud Dialogflow CX integration, and limited SSML (Speech Synthesis Markup Language) support—SSML is not supported in call flows, secure call flows, and queue flows, though it is available with third-party TTS providers in bot flows only. PCI-DSS compliance requirements vary by integration. Amazon Polly, Google Cloud Text-to-Speech, Microsoft Azure Cognitive Services TTS, Genesys Enhanced TTS, and Nuance Text-to-Speech are PCI-compliant and usable in secure flows. Acapela Voice and Speech Morphing are not PCI-compliant and cannot be used in secure flows. Configuration involves installing integrations from the AppFoundry, activating them within Genesys Cloud, and designating a default engine at the organizational level. Administrators can then configure specific engines and voices for individual flows, test third-party TTS engine playback, and search for flows utilizing specific TTS engines through the Architect interface

Feature coming soon: Genesys Generative TTS

Use the default Genesys text-to-speech (TTS) engine, or add third-party TTS engine integrations. Select from the available voice options. By default, the organization’s TTS engine is Genesys TTS. To access more third-party TTS engines in Architect, first obtain them from the Genesys AppFoundry. Then configure them in Genesys Cloud. Select from the available voice options.

Notes:

Currently, custom text-to-speech (TTS) voices are incompatible with Google Cloud Dialogflow CX integration, including Genesys Enhanced TTS and Genesys TTS Connector.
Genesys Cloud does not support SSML (Speech Synthesis Markup Language) in call flows, secure call flows, and in queue flows. However, Genesys Cloud supports SSML with third-party TTS provider integrations in bot flows only, for example when using Amazon Polly TTS.
The maximum TTS request length supported by Genesys Cloud is 3,000 characters.

TTS overview

Learn about TTS engines and options.

Genesys Enhanced TTS

Genesys Enhanced TTS is the optional Genesys Cloud text-to-speech engine. Your organization is billed for this feature only if you use it. After you accept the terms and conditions from the AppFoundry, you can select Genesys Enhanced TTS in voice and bot flows. This feature is PCI-DSS compliant and you can use it in secure call flows.

Genesys Enhanced TTS pricing

Learn more about Genesys Enhanced TTS pricing. Pricing information can be found in the Add-ons > Genesys Enhanced TTS section of the Genesys Cloud pricing hub.

Genesys Cloud pricing hub

Genesys Generative TTS

Genesys Generative TTS is the optional Genesys Cloud generative text-to-speech engine. This feature enables customers to deliver more natural, human-like TTS experiences. You can select Genesys Generative TTS in voice and bot flows.

Select a TTS engine and voice for a flow

Genesys TTS Connector

Install the Genesys TTS Connector integration and then configure it to use your preferred third-party text-to-speech engine with Genesys Cloud.

Amazon Polly integration

Install the Amazon Polly integration and then configure it for use with Genesys Cloud. Amazon Polly is PCI-compliant and can be used in secure flows. Genesys Cloud support includes Neural and Generative voices.

Acapela Voice integration

Install the Acapela Voice integration and then configure it for use with Genesys Cloud. The Acapela Voice integration is not PCI-compliant and therefore cannot be used in secure flows.

Google Cloud Text-to-Speech integration

Install the Google Cloud Text-to-Speech integration and then configure it for use with Genesys Cloud. This feature is PCI-DSS compliant. You can use this integration in secure call flows. For more information, see PCI DSS compliance.

Microsoft Azure Cognitive Services Text-to-Speech (TTS) integration

Install the Microsoft Azure Cognitive Services text-to-speech (TTS) integration and then configure it for use with Genesys Cloud. This feature is PCI-DSS compliant. You can use this integration in secure call flows. For more information, see PCI DSS compliance.

Nuance Text-to-Speech integration

Install the Nuance Text-to-Speech integration and then configure it for use with Genesys Cloud. This feature is PCI-DSS compliant. You can use this integration in secure call flows. For more information, see PCI DSS compliance.

Speech Morphing integration

Install the Speech Morphing integration and then configure it for use with Genesys Cloud. The Speech Morphing integration is not PCI-compliant and therefore cannot be used in secure flows.

Select a TTS engine for the organization

After you install a TTS integration from the AppFoundry, select it as the default engine for the organization.

Work with TTS engines in Architect

Learn about TTS and language selection, select a TTS engine and voice for a flow, and search for flows that use a specific TTS engine.

[NEXT] Was this article helpful?

Get user feedback about articles.