Penguin Solutions said it has entered a strategic collaboration with Deepgram and Dell to design and deploy production-ready AI inference infrastructure for enterprise voice AI. The deployment uses Dell PowerEdge servers and Dell PowerScale storage to support Deepgram’s speech-to-text, text-to-speech, and voice agent services. The infrastructure includes Dell PowerEdge XE7745 systems with NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs for real-time inference workloads. Joe Castillo of Penguin Solutions said the partners developed an architecture intended to meet enterprise service-level requirements such as low latency and high concurrent usage. Abe Pursell of Deepgram said the infrastructure was designed to align with Deepgram’s performance, scalability, and reliability requirements.

Disclaimer: This news brief was created by Public Technologies (PUBT) using generative artificial intelligence. While PUBT strives to provide accurate and timely information, this AI-generated content is for informational purposes only and should not be interpreted as financial, investment, or legal advice. Penguin Solutions Inc. published the original content used to generate this news brief via Business Wire (Ref. ID: 20260317793434) on March 17, 2026, and is solely responsible for the information contained therein.