Skip to main content

Genesys Cloud – Addition of Deepgram Flux and Nova-3 speech-to-text (STT) engines and updated STT engine names

Announced on
(YYYY-MM-DD)		Effective date
(YYYY-MM-DD)		Aha! idea
2026-07-06 - -

In a future release, Genesys Cloud will add two new speech-to-text (STT) engines for Architect bot flows and rename the existing STT engine options to more accurately reflect the underlying speech recognition providers. These updates give organizations additional STT choices while making it easier to identify the technology used by each engine. Existing bot flows continue to work without changes.

What’s changing

Genesys Cloud adds the following STT engines for Architect bot flows:

  • Deepgram Flux
  • Deepgram Nova-3

You can use these engines with bots, virtual agents, and agentic virtual agents in Architect.

Genesys Cloud also renames the existing STT engines as follows:

Current nameNew name
Genesys Enhanced v1Google Cloud
Genesys Enhanced v2Microsoft Azure
Genesys Enhanced v3Amazon Transcribe
Genesys Enhanced v4Genesys Native

These are name changes only. Existing bot flows continue to function without modification, and there are no changes to engine behavior, accuracy, or configuration.

Note: When you use Deepgram Flux or Deepgram Nova-3, Deepgram processes the audio. Depending on the endpoint that you configure, audio traffic may be processed outside your Genesys Cloud region. Customers with data residency or compliance requirements should review the Deepgram regional endpoint documentation before enabling either engine in production.

Action required

No action is required for existing STT engine configurations.

If you plan to use Deepgram Flux or Deepgram Nova-3, review the documentation and confirm that the selected endpoint meets your organization’s data residency and compliance requirements before enabling the engine in production.

Notification of new sub-processor