KUGELAUDIO'S EXCLUSIVE PARTICIPATION
Masterclass
Reliable Voice AI at Scale: Models, Infrastructure, and On-Prem Deployment
Agentic AI Demo
Kugel Fluid; Fully On-Prem and Air-Gapped
ABOUT KUGELAUDIO
Berlin-based KugelAudio, backed by Y Combinator, trains its own speech models for enterprise contact centers. Run them in our cloud or on your own servers, even offline. Germany's biggest telecom providers already use them.
AGENTIC AI DEMOS
Kugel Fluid
Kugel Fluid is a leading European speech-to-speech model, trained in Berlin and built to compete with OpenAI's Live API. It is full-duplex, so it listens while it speaks and handles interruptions naturally, with a voice that breathes and gets complex names and numbers right. You choose which LLM it works with, and the official OpenAI SDK works with a KugelAudio key. Come by and try it out!
Fully On-Prem and Air-Gapped
All KugelAudio models run fully on-premises in your own infrastructure, even air-gapped. That includes Kugel Fluid as well as our speech to text and text to speech models. Call audio and customer data never leave the building. Built for regulated industries, telecom providers, the public sector and everyone else who needs full control. sipgate already runs KugelAudio in production in its own private cloud.
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.
15:00 - 15:30
Thu, Nov 26
Reliable Voice AI at Scale: Models, Infrastructure, and On-Prem Deployment
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.
HIGHLIGHT SESSION
REGISTER
AI BUYERS / USERS
FREE
🎁 Free Pro Max Pass
🎓 All Sessions Access
🤖 AI Success Stories
🥂 Exclusive Reception Event
🤝 Accept 1:1 Meetings (3 x 15 mins each)
"👔 For senior enterprise leaders shaping the future of voice, audio, and conversational AI adoption.
Includes: Chief Technology Officers, Chief Digital Officers, VPs of Product & Innovation, Heads of AI & Machine Learning, Chief Compliance & Legal Officers, and Senior Strategy Leaders in media, entertainment, telecom, and global enterprises."
AI PRACTITIONERS
DISCOUNTED
💸 Discounted Pro Max Pass
🎓 All Sessions Access
🤖 AI Workshops
🥂 Exclusive Reception Event
🤝 Book AI Demos
🎟️ Use coupon code: AMS26KUGEL at checkout
🧠 For practitioners and managers building and deploying voice AI solutions.
Includes: Product Managers, Voice UX Designers, Software Developers, Audio Engineers, Content & Localization Managers, and Technical Leads integrating ElevenLabs technologies.
.png)