Default speech recognition settings

AI-generated summary

Genesys Cloud's speech recognition settings can be configured within a call flow's general configuration under the Recording and Speech Recognition section. Key features include call recording suppression, verbal selection capabilities, and company directory speech recognition options. The system allows customization of speech recognition parameters including minimum confidence levels, match timeouts, and maximum speech duration. Company directory speech recognition can be enabled for the entire flow or specific menus/tasks, requiring custom prompts to instruct callers about speaking names. When enabled, the flow listens for company directory inputs in menus and Collect Input actions. The platform includes configurable timeout settings for both complete and incomplete matches, ensuring proper handling of caller speech inputs. Call recording can be suppressed for entire flows through a default-enabled checkbox setting.

Within a call flow’s general configuration, you can configure speech recognition settings. These settings are available in the Recording and Speech Recognition section of a flow’s Settings area.

Name	Description and use
Suppress recording for the entire flow	If call recording is enabled, check this box to suppress call recording for the entire flow. This setting is enabled by default.
Enable speech recognition for the entire flow	Check this box to allow callers to verbally indicate their selection in this flow. This setting is enabled by default.
Company Directory speech recognition	Optionally select to enable company directory speech recognition for the entire flow, or just for the starting menu or task. This setting is enabled by default, and disabled when Enable speech recognition for the entire flow is unchecked. When you enable the company directory speech recognition setting for the entire flow, the flow listens for the company directory in menus and Collect Input actions. To prompt callers to say the name of the person they want to reach, the flow must tell the caller when speech recognition for the company directory is enabled. Architect does not provide automatic prompts for use when this feature is enabled--you must include instructions for the user in your recorded prompts. For example, "you can speak the name of the person you would like to reach at any time."
Minimum confidence level	Adjust the minimum confidence level, or the highest scoring the phrase must receive to achieve a successful match.
Complete match timeout	Set the maximum time to wait after caller provides a valid speech input and stops talking before the system presents a positive match.
Incomplete match timeout	Choose the length of time to wait after caller stops talking and when the verbal selection is invalid before the system indicates no match is found.
Maximum speech length	Choose the amount of time to allow a caller to say a word or phrase.

[NEXT] Was this article helpful?

Get user feedback about articles.

Loading...

Default speech recognition settings

[NEXT] Was this article helpful?