Speech-to-text (STT) engines overview
Speech-to-text engines recognize and analyze audio in real-time or offline to transcribe spoken words into text. Use a speech-to-text integration, for example, if you use your own or a third-party chat bot that you want to use for voice bot conversations.
- Before you can obtain the Microsoft Azure premium application, you must contact Genesys Cloud Sales to add BYOT Rate E to your subscription. For more information, see Bring your own technology services model (per turn/minute rates).
- Speech-to-text engines are only available in Architect for Genesys Dialog Engine Bot Flows.
Genesys Enhanced STT engines
Genesys Cloud natively offers three versions of the Genesys Enhanced STT engines. The following table lists each version and its corresponding STT service provider:
| Genesys Enhanced STT version | Vendor name | Custom ASR dictionary support |
|---|---|---|
| Genesys Enhanced v1 | Google Cloud Speech-to-Text STT | |
| Genesys Enhanced v2 (Default) | Microsoft Azure Cognitive Services STT | |
| Genesys Enhanced v3 | AWS Transcribe STT |
If you want to use a custom ASR dictionary, you must choose Genesys Enhanced v3. For more information about managing your custom dictionaries, see Understand dictionary management.
Bot Transcription Connector
- Genesys does not charge for the use of Bot Transcription Connector itself. Customers are responsible for any usage and processing fees charged by their selected third-party STT vendor, as well as for any one-time development effort required to integrate their STT solution using Bot Transcription Connector.
- Bot flow usage charges (for Genesys Dialog Engine Bot Flows) continue to apply as part of standard platform pricing. For more information, see Genesys Dialog Engine Bot Flows and Genesys Digital Bot Flows pricing overview.
Bot Transcription Connector allows you to integrate third-party ASR engines using the Genesys AudioHook protocol. You can select a third-party ASR engine in Genesys Dialog Engine Bot Flows either as the default engine or for specific slot collection using an Ask for Slot action. This feature provides you with fine-grained control over speech recognition quality.
Third-party STT integrations
Add a speech-to-text integration from AppFoundry and then use it in Genesys Dialog Engine Bot Flows for real-time recognition. Use the transcribed utterances to voice-enable an external chat bot. Data actions can send the transcribed customer utterances to the chat bot, and then the bot replays the results to the customer using text-to-speech.
Data actions integrations allow you to create custom actions in Genesys Cloud that you can use throughout Genesys Cloud to act on data in your CRM. For more information, see About integrations.
[NEXT] Was this article helpful?
Get user feedback about articles.