Abstract
Voice AI often performs well in demos but fails in production on the details that matter: names, numbers, email addresses, specialist terminology, latency, and data privacy. This session explores how to build and deploy reliable voice AI for enterprise customer operations, with a particular focus on secure on-premise deployment. Drawing on real-world customer deployments, it covers model quality, evaluation methods, infrastructure requirements, and operational reliability in regulated environments. Attendees will learn which benchmarks actually matter, where voice systems commonly break, and how to move from an impressive prototype to a production-ready voice experience.
Topics To Be Covered
Evaluate voice AI beyond benchmark scores
Design reliable enterprise voice AI systems
Reduce latency while maintaining accuracy
Deploy voice AI securely on-premises
Avoid common production deployment pitfalls
Perfect For
AI and Voice AI engineers
Conversational AI architects
Customer service technology leaders
Enterprise AI decision-makers
Platform and infrastructure teams
Meet Your Speaker
Viktor Presber
Co-Founder, KugelAudio
Viktor is the co-founder of KugelAudio, a Y Combinator-backed company building high-performance voice AI models for European languages. He works closely with customers on-site to understand real-world requirements and make voice AI systems reliable in production.
At KugelAudio, he focuses on enterprise deployments where accuracy, latency, data privacy, and operational reliability are critical. The company has a clear focus on on-premise deployment, enabling organizations to run advanced voice AI within their own infrastructure and retain full control over sensitive data.
ADDITIONAL INFORMATION
Time & Place
Thu, Nov 26
15:30 - 16:00
Matterhorn I
Limited to 45 participants.
Secure your seat – registration required.
Notes
Agenda for this session
20 min presentation + Audience Q&A
.png)