About speech-to-text (STT) engines

AI-generated summary

Genesys Cloud includes industry-standard speech-to-text (STT) engines that recognize and analyze audio in real time or offline to transcribe spoken words into text. The platform offers three primary STT implementation options: included STT engines available across major developer platforms and enterprise solutions; Bring Your Own Technology (BYOT) STT engines that enable integration of third-party transcription services into bot flows and voice architectures using per turn/minute pricing models; and the Bot Transcription Connector, which streams audio from bot flows to third-party Automatic Speech Recognition (ASR) engines and receives transcripts back via the Genesys AudioHook protocol. Users can select specific STT engines and voices for bot flows within Architect, search for bot flows using particular STT engines, manage dictionaries for improved accuracy, and configure advanced ASR settings. The platform supports multiple languages and integrates with AWS regions. Installation and configuration of the Bot Transcription Connector is available through the Integrations page, with pricing details provided for Genesys Dialog Engine Bot Flows and Genesys Digital Bot Flows.

Speech-to-text engines recognize and analyze audio in real time or offline to transcribe spoken words into text. Genesys includes some established industry-standard speech-to-text (STT) engines. You can also use Bring Your Own Technology (BYOT) STT engines, which enable you to bring your own STT or Automatic Speech Recognition (ASR) engines and then integrate them in Architect bot flows. Finally, use the Bot Transcription Connector to stream audio from bot flows to a third-party ASR engine and receive transcripts back using the Genesys AudioHook protocol.

STT overview

Learn about STT engines and options. Learn about STT and language selection. Select a STT engine and voice for a bot flow, and search for bot flows that use a specific STT engine.

Included STT engines

Use the industry-standard STT engines available across major developer platforms and enterprise solutions.

BYOT STT engines

Use Genesys Cloud to integrate third-party transcription services into bot flows and voice architectures.

Bot Transcription Connector

Use the Bot Transcription Connector integration to stream audio from bot flows to a third-party Automatic Speech Recognition (ASR) engine and receive transcripts back.

[NEXT] Was this article helpful?

Get user feedback about articles.