Machine Learning Chips & Compute8 min reading time

How Deepgram optimized voice AI at scale with AWS Trainium

AWS BlogPublished 3 hours ago

Deepgram optimized its Nova-3 speech-to-text AI model for AWS Trainium2 chips, achieving 11–70% more audio processed per dollar on batch workloads. This efficiency gain helps Deepgram serve over 200,000 developers and 1,400 organizations more cost-effectively through its API and Amazon SageMaker AI.

#amazon-sagemaker-ai #aws-trainium2 #cloud-computing #deepgram #nova-3 #speech-recognition

How Deepgram optimized voice AI at scale with AWS Trainium

More in Machine Learning

Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster

Nvidia launches new open models to run agents in the enterprise and on PCs

AI researchers stranded Claude on a virtual desert island. It started to “play.”