Experience · Data artifact
Voice Persona Profile
Data artifactExperienceExperience & Human Oversightarc:VoicePersonaProfile
A configuration of voice identity, pitch, speaking rate and prosody settings that expresses an agent persona or a user's accessibility preference in synthesized speech.
Responsibility. Defines how an agent sounds when it speaks.
Also known as: Voice customization settings, Prosody configuration
Relationships
configures structural
Design guidance
- SHOULD match persona (e.g., lower pitch and slower rate for financial advisory, higher pitch and faster rate for retail) and MAY follow user preference for accessibility.
Classification
- Patterns
- Persona-specific voice design
- Technologies
- SSML-style prosody controls in Riva TTS
- Quality attributes
- Interaction capability (ISO/IEC 25010)
Sources
- Ch7.5: T. Nguyen, "NeMo Curator, Riva Speech AI & Multimodal Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.5. ISBN: 9798244538229.