Orange Business Partners with NVIDIA for Voice AI Inference

Orange Business and NVIDIA are collaborating on distributed voice artificial intelligence inference to help enterprises deploy natural, real-time conversational agents with lower latency, greater resilience, and more control over where AI services run.

The approach distributes AI models across central cloud and regional point of presence (PoP) resources. This enables a natural conversational flow by reducing latency, while optimizing GPU capacity and bandwidth use, and helps keep voice data local where required.

AI models are accessed through Live Intelligence, Orange's secure multi-large language model trusted AI platform, while the AI Distributed Inference platform manages workloads across central-cloud and regional PoP resources. Integrated routing balances traffic between sites and can redirect requests if a site is unavailable or overloaded.

To build this solution, Orange Business is integrating NVIDIA Nemotron models into Live Intelligence. In addition, Orange Business brings together the network, cloud and regional infrastructure, model management, and request routing required to operate distributed AI services end to end. This gives customers greater control over data processing, service operations, and AI deployment locations, supporting data-residency and sovereignty requirements.

The service is designed to support other applications, including emergency communications, live multilingual translation, enterprise contact centers, video analytics, drone detection, computer vision, and industrial IoT.

"Distributed infrastructure is the next frontier of the AI factory buildout, as demand for inference and edge computing accelerates," said Ronnie Vasishta, senior vice president of telecom at NVIDIA, in a statement. "Telcos are uniquely positioned to become distributed infrastructure service providers. With NVIDIA, Orange is expanding from the central to distributed sites, powering a new class of real-time intelligence applications that need deterministic performance, reliability and scale, and can be delivered together with connectivity using the AI-RAN architecture."

"Distributed inference will be a critical part of the next phase of enterprise AI. It requires compute, connectivity, and orchestration across multiple sites and regions," said Anne-Marie Thiollet, chief product and marketing officer of Orange Business, in a statement. "Our extensive network and infrastructure footprint enable us to combine these capabilities together and help customers deploy AI services with greater performance, resilience, and control."