Machine Learning Chips & Compute8 min reading time

How Deepgram optimized voice AI at scale with AWS Trainium

AWS BlogPublished 6 days 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

PyTorch Conference 2026: Google and Meta Open-Source TorchTPU for Native PyTorch on TPUs

Hugging Face Releases Carbon-X, a 14B Open DNA Language Model that Brings DNA and Natural Language Together for the First Time

Google ML Drift Accelerates On-Device AI Inference Across Diverse GPUs