Configure Virtual Agent-Voice in Webex Contact Center

Publisher

Cisco Systems, Inc. (Webex Help Center)

URL

https://help.webex.com/en-us/article/n6gaghu/Configure-Virtual-Agent-Voice-in-Webex-Contact-Center

Published

2026-07-17

Updated

unknown

Accessed

2026-09-04

HTTP status

200

License

Cisco proprietary documentation, all rights reserved; no-redistribution; short excerpts and locators only

Source notes citing this source

• Webex Contact Center Virtual Agent Voice default system settings are: DTMF termination symbol #, DTMF no-input timeout 5 seconds, DTMF inter-digit timeout 3 seconds, and barge-in enabled. in context
• Webex Contact Center Virtual Agent Voice can be backed by Google Dialogflow CX, Google Dialogflow ES, or a Bring Your Own Virtual Agent (BYOVA) integration. in context
• The Webex Contact Center Virtual Agent V2 flow activity has three outcomes: Handled when the virtual agent execution completes, Escalated when the call must go to a human agent, and Errored for any error scenario. in context
• In the Dialogflow CX Virtual Agent V2 configuration section, the article states English (en-US) is currently the only supported language and only the u-law codec is supported. in context
• Integrating with Dialogflow ES specifically requires the customer to have the Dialogflow Essentials edition. in context
• Administrators can override the default VAV input language and output voice per-flow using Set Variable activities before the Virtual Agent V2 activity, setting Global_Language (e.g. fr-CA) and Global_VoiceName (e.g. en-US-Standard-D). in context
• Integrating any VAV provider requires 2 prerequisites: configuring a service-provider-specific Integration Connector (e.g. Google CCAI connector) in Control Hub, and creating a Contact Center AI (CCAI) configuration, which generates a CCAI config ID used in Flow Control. in context
• Webex Contact Center's Virtual Agent-Voice currently supports 3 integration paths: Google Dialogflow CX, Google Dialogflow ES, and Bring Your Own Virtual Agent (BYOVA). in context
• Virtual Agent V2 has several fixed, non-configurable system defaults: infinite retries on invalid/no-input errors, barge-in enabled, DTMF termination symbol '#', DTMF no-input timeout of 5 seconds, and DTMF inter-digit timeout of 3 seconds. in context
• The Virtual Agent V2 flow activity has 2 outcome paths -- 'Handled' (virtual agent execution completed) and 'Escalated' (call must be escalated to a human agent) -- plus an 'Errored' error-handling path. in context
• The Virtual Agent V2 activity must not be placed immediately after a Queue Contact activity, and must not be placed in the Event Flow canvas -- both configurations are explicitly unsupported. in context
• Placing the Virtual Agent V2 activity immediately after a Queue Contact activity, or in the Event Flow canvas, produces no runtime warning even though both configurations are unsupported. in context
• A deployment that needs non-English voice self-service has, on Cisco's current documentation, a documented language path on Webex AI Agent but not on the Dialogflow CX Virtual Agent-Voice integration. inferred in context
• With Dialogflow CX, Webex Contact Center supports partial response, custom event, custom parameters and custom payload. in context
• Global_Language and Global_VoiceName global variables set the input language and output voice for Virtual Agent V2, and can be overridden with Set Variable activities placed before the activity. in context
• Cisco's Virtual Agent-Voice article states that en-US is currently the only supported language. in context
• The Virtual Agent V2 activity has three outcome paths: Handled when the virtual agent execution completes, Escalated when the call must go to a human agent, and Errored for any error. in context
• The Virtual Agent V2 activity outputs VirtualAgentV2.TranscriptURL, VirtualAgentV2.MetaData (JSON received from the bot during fulfillment or custom event handling) and VirtualAgentV2.StateEventName. in context
• The Virtual Agent V2 activity cannot be placed after a Queue Contact activity and cannot be placed in the Event Flow canvas. in context
• Before configuring the Virtual Agent V2 activity with Dialogflow CX, the Google CCAI connector and a CCAI feature configuration (which generates the config ID used in flows) must exist, along with an entry point and routing flow. in context
• The Virtual Agent V2 State Event settings have optional Event Name and Event Data (JSON) fields that send a custom event to the AI platform, and accept {{ variable }} expressions. in context
• The Virtual Agent V2 activity selects its CCAI configuration either statically from a dropdown of configured CCAI features or through a Variable Contact Center AI Config chosen at run time, for example by caller PSTN region. in context
• Non-configurable Virtual Agent V2 defaults include infinite retries on invalid or no input, barge-in enabled, # as DTMF termination, a 5-second no-input timeout and a 3-second inter-digit timeout. in context
• The Virtual Agent-Voice article gives Termination Delay a range of 0-30 seconds with a default of 30 seconds. disputed in context
• The virtual agent transcript appears in Agent Desktop only if Enable Conversation Transcript is on and an Agent Says fulfillment response is configured in Dialogflow CX. in context
• Virtual Agent-Voice supports only the u-law codec. in context
• Cisco lists barge-in as enabled by default, letting the caller interrupt the Virtual Agent. in context
• Cisco states that the Virtual Agent V2 DTMF settings are defined internally, do not appear in the user interface and cannot be changed, and that they apply to Dialogflow CX, Dialogflow ES and BYOVA. in context
• For the Virtual Agent V2 activity, the system-defined DTMF inter-digit timeout is 3 seconds, after which the virtual agent moves on in the conversation. in context
• For the Virtual Agent V2 activity, the system-defined DTMF no-input timeout is 5 seconds. in context
• For the Webex Contact Center Virtual Agent V2 activity, the system-defined DTMF termination symbol is #. in context
• The Virtual Agent V2 DTMF defaults are documented for Google Dialogflow CX, Google Dialogflow ES and Bring Your Own Virtual Agent. in context
• Virtual Agent V2 uses fixed DTMF defaults: # as the termination symbol, a 5-second no-input timeout, a 3-second inter-digit timeout, barge-in enabled and an infinite number of retries for invalid or no input. in context
• The Virtual Agent V2 default DTMF settings do not appear in the user interface and cannot be changed. in context
• Because Virtual Agent V2 retries invalid or missing DTMF input an unlimited number of times and the setting cannot be changed, a retry cap before a default route cannot be set on that activity and has to come from the bot's own design. inferred in context
• Checking Enable Conversation Transcript on the Virtual Agent V2 activity lets Agent Desktop display the transcript of the conversation between the virtual agent and the caller. in context
• Cisco says not to place a Virtual Agent V2 activity after a Queue Contact activity or in the Event Flow canvas. in context
• At system level the Virtual Agent V2 activity enables barge-in, allows infinite retries for invalid or no input, and uses # as the DTMF termination symbol. Administrators cannot change these. in context
• The Virtual Agent V2 system-level no-input timeout is fixed at 5 seconds and the inter-digit timeout at 3 seconds. Administrators cannot change either. in context
• The Virtual Agent-Voice article's Limitations section states that en-US is currently the only supported language. in context
• The Enable Conversation Transcript check box on the Virtual Agent V2 activity lets Agent Desktop display the transcript of the conversation between the virtual agent and the caller. in context
• To change the virtual agent conversation language, a Set Variable activity sets the Global_Language variable to the required language code (the documented example is fr-CA) before the Virtual Agent V2 activity. in context
• To change the synthesized voice, a Set Variable activity sets the Global_VoiceName variable to the required output voice name code, for example en-US-Standard-D. in context
• Inference: Cisco's Virtual Agent-Voice article both documents Global_Language with a fr-CA example and states en-US is the only supported language, so whether non-en-US Dialogflow CX conversations are supported cannot be settled from this page alone. inferred in context
• Inference: documented constraints that could each produce silence or a non-answering virtual agent are a missing CCAI config or connector, a tenant region outside the listed CCAI regions, a non-u-law media path, and placing the activity after Queue Contact or in the Event Flow. inferred in context
• Cisco instructs administrators not to place a Virtual Agent V2 activity after a Queue Contact activity in a flow. in context
• Cisco instructs administrators not to use the Virtual Agent V2 activity in the Event Flow canvas. in context
• The Virtual Agent V2 activity's Errored output is the path the flow takes in any error scenario. in context
• The Virtual Agent V2 activity takes its Escalated outcome when the call must be escalated to a human agent. in context
• The Virtual Agent V2 activity takes its Handled outcome when the virtual agent execution completes. in context
• The output variable VirtualAgentV2.StateEventName stores the name of the custom event that the system receives back from the agent bot. in context
• The Virtual Agent V2 output variable VirtualAgentV2.TranscriptURL stores the URL of the transcript of the conversation between the virtual agent and the caller. in context
• Before using Virtual Agent-Voice the administrator must configure the provider's integration connector (for example the Google CCAI connector) and create a Contact Center AI (CCAI) feature in Control Hub, which generates the CCAI config ID used in the flow. in context
• The State Event settings of the Virtual Agent V2 activity send a custom event to the AI platform as an Event Name plus Event Data in JSON (documented example: CustomWelcome with {"Name": "John"}). in context
• In the Virtual Agent V2 activity Conversational Experience settings, a Static Contact Center AI Config uses the default PSTN region while a Variable Contact Center AI Config selects the CCAI config dynamically, for example based on the caller's region. in context
• The Virtual Agent V2 activity's Termination Delay accepts 0 to 30 seconds with a default of 30. It lets the virtual agent complete its last message before the activity stops and the flow moves to the next step. in context
• When a call is transferred to a live agent, the virtual agent transcript appears in the Transcript gadget on Agent Desktop, which requires the Transcript gadget to be configured in the desktop layout. in context
• The Virtual Agent-Voice Limitations section states that only the u-law codec is supported. in context
• Virtual Agent-Voice in Webex Contact Center supports three integrations: Google Dialogflow CX, Google Dialogflow ES and Bring Your Own Virtual Agent (BYOVA). in context

Cite this source record

APA

WarmTransfer. (2026, July 17). Configure Virtual Agent-Voice in Webex Contact Center. WarmTransfer. https://warmtransfer.net/knowledge/sources/cisco-help-n6gaghu-wxcc-virtual-agent-voice

BibTeX

@misc{warmtransfer-cisco-help-n6gaghu-wxcc-virtual-agent-voice,
  title  = {Configure Virtual Agent-Voice in Webex Contact Center},
  author = {{WarmTransfer}},
  year   = {2026},
  url    = {https://warmtransfer.net/knowledge/sources/cisco-help-n6gaghu-wxcc-virtual-agent-voice},
  note   = {Cisco Systems, Inc. (Webex Help Center), accessed 2026-09-04}
}