To configure Agentic Voice:

1. Ensure the following configuration is complete:

   • Configuring Vault AI in CRM
   • My Notes
   • Voice Dictionary Entries

2. Ensure users have Execute permission to the Voice Agent:

• Navigate to Admin > Users & Groups > Permission Sets
• Select the appropriate permission set
• Select the Agents tab
• Select the Execute checkbox for the Voice Agent (voice_agent__v)

3. Activate the Voice Agent:

   • Navigate to Admin > Configuration > Vault AI Setup > Agents
   • Select the Voice Agent
   • Select Edit
   • Select Active in the Status picklist

When Voice Agent and Key Medical Insights are both enabled for a user, the Dictate Medical Insight option always displays in Agentic Voice menus.

To ensure Agentic Voice correctly recognizes and transcribes specific pronunciations—for example, unique product names, abbreviations, and regional or company-specific phrases—admin users create Voice Dictionary Entries. These entries can be applied across the Vault CRM instance or applied only to specific user languages and countries. For more information, see Voice Dictionary Entries.

Agentic Voice natively transcribes standard medical terms and common proper nouns without requiring a specialized medical dictionary; however, abbreviations, unique brand names, and abbreviations-as-proper-nouns are not automatically recognized and must be added as a Voice Dictionary Entry to ensure accurate transcription.

All Vault CRM Supported Languages are also supported for the user interface, generated content, and CRM interactions. However, speech recognition quality depends on the language and region combinations that Apple iOS officially supports.

To ensure successful call transcription and accurate voice dictionary mapping, make sure the following all match:

• Language the user speaks
• Language set on the Vault User record (language__sys field on the user__sys record)
• iOS device language and region, found under Settings on the user's iOS device
• Active keyboard and dictation language, found under Settings on the user's iOS device

Mixed-language configurations or content are not supported and can cause transcription or mapping failures. Veeva does not guarantee performance or accuracy for language and region combinations not supported by Apple iOS, or provide technical support for unsupported speech-to-text locales.

If the device language and region combination is not supported by iOS speech recognition, users receive an alert notifying them that transcription is not supported in their device's language when they attempt to capture voice dictation. To resolve the issue, update the device language and region to match.