Penguin Solutions Inc. (NASDAQ: PENG) announced a collaboration with Deepgram and Dell Technologies to deploy AI inference infrastructure for enterprise voice applications. The partnership combines Dell PowerEdge servers and NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs to support Deepgram's speech-to-text, text-to-speech, and voice agent capabilities.

The infrastructure deployment targets mission-critical applications in healthcare and retail sectors, addressing enterprise requirements for low latency and high concurrent usage in real-time voice processing environments.

"Modern AI workloads demand infrastructure that performs consistently and scales predictably under heavy loads, particularly for real-time inference applications like voice agents," said Joe Castillo, vice president of sales at Penguin Solutions.

The architecture incorporates Dell PowerScale storage and Dell PowerEdge XE7745 servers with NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. The solution aims to enable data-intensive voice applications to operate in real-time environments while maintaining strict service level agreements.

Abe Pursell, vice president of partnerships and business development at Deepgram, stated that Penguin Solutions demonstrated understanding of their technical requirements and translated them into an infrastructure environment that supports enterprise-class capabilities.

The collaboration represents a comprehensive approach for enterprises seeking to modernize customer and employee experiences through API-driven voice capabilities, AI services, and AI infrastructure components.

The companies will present their collaboration at the NVIDIA GTC AI Conference and Expo on March 17 at Dell's booth, with a session titled "Powering Enterprise Voice AI: Deepgram's Agentic Solution."