To configure Agentic Voice:

1. Ensure Configuring Vault AI in CRM is complete.

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. Select the Objects tab.

4. Grant the following permissions:

   Object	Object Permission	Object Types	Fields	Field Permission
   voice_dictionary_entry__v	R	core_object_type__v	All Fields	Read

5. Verify the appropriate agent actions are Active for the agent:

• Navigate to Admin > Configuration > Vault AI Setup > Agents
• Select the Voice Agent
• Select Edit
• Select Active in the Status picklist
• Select Save
• Expand the Actions section
• Verify the Transpose Call action is active:
  • Transpose Call - Takes users’ dictated Call Voice Note transcriptions and transposes them into a call report

6. Navigate to Business Admin > Objects > vmobile_object_configuration__v.

7. Ensure voice_dictionary_entry__v VMOCs are active for the appropriate platforms.
8. Navigate to Business Admin > Objects > Veeva Messages.
9. Add MyNotes to the TAB_NAV_DISPLAY Veeva Message, if Managing Tab Visibility and Display Order is enabled.

To ensure Agentic Voice correctly recognizes and transcribes specific pronunciations—for example, product names, medical terms, 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.

Each entry includes:

• Phrase – The written spelling of the word or phrase (for example, Natevba)
• Pronunciation – The word’s pronunciation, written using the X-SAMPA Transcription Scheme, a standardized way to represent speech sounds using plain text characters

X-SAMPA (Extended Speech Assessment Methods Phonetic Alphabet) provides a device-independent way to specify pronunciations. It ensures consistency across regions and languages, even when device or platform-level phoneme support differs.

For example, in an organization with product names like Cholecap, Restolar, and Natevba, an admin would populate the Phrase and Pronunciation on a Voice Dictionary Entry as follows:

Phrase	Pronunciation (X-SAMPA Transcription)
Cholecap	k"ol@k{p
Restolar	r"Est%olAr
Natevba	n"OtEvbO

Because iOS phoneme support varies by region and device, some X-SAMPA symbols may not be supported everywhere. Vault CRM does not validate phoneme compatibility, so unsupported symbols may result in incorrect or unrecognized pronunciations.

Veeva recommends testing the Voice Dictionary Entries with end users who reflect the full range of accents, dialects, and languages in use before making Agentic Voice available to all users.

To create Voice Dictionary Entries for custom pronunciations:

1. Navigate to Business Admin > Objects > voice_dictionary_entry__v.

2. Select Create.

3. Populate the Phrase field with the phrase or word’s written spelling. For example, Natevba.

4. Populate the Pronunciation field with the phrase or word’s pronunciation, using the X-SAMPA Transcription Scheme.

5. Select a Language and/or Country for the entry (optional):

• Languages are matched to the language__sys field on the user’s user__sys record. If a language is not selected on the Voice Dictionary Entry, the entry applies to all user languages.
• Countries are matched to the country__sys field on the user__sys record. If a country is not selected on the Voice Dictionary Entry, the entry applies to all user countries.
• If both the Language and the Country fields are left blank on a Voice Dictionary Entry, the entry applies to all languages and countries

6. Select Save.

All Vault CRM Supported Languages are also supported for Agentic Voice user interface, generated content, and CRM interactions. However, device language and locale configuration determine the spoken language recognized by Agentic Voice, not the user’s Vault CRM language setting. Because of this, speech recognition quality and the available languages depend on the language and locale 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)
• iOS device language
• Active dictation keyboard language

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