How Deepgram optimized voice AI at scale with AWS Trainium
AWS Machine Learningen

Deepgram worked with the AWS Forward Deployed Engineering team to port its Nova-3 speech-to-text model to AWS Trainium2 for offline batch inference. This post covers porting to the AWS Neuron stack, kernel-level tuning, a data-parallel Rust runtime, and the throughput and cost results on batch transcription.
This is a short summary published by AI Global Wire. The full article is owned and hosted by AWS Machine Learning — open it there to read it in full.
Read the full story at AWS Machine LearningRelated AI news
- Pegasus 1.5 from TwelveLabs is now available in Amazon BedrockAWS Machine Learning · October 19, 2026
- Push-based KV transfer to improve TTFT and TPOT for disaggregated inference in vLLMAWS Machine Learning · October 19, 2026
- Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLMAWS Machine Learning · October 19, 2026
- Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCoreAWS Machine Learning · October 16, 2026
- Introducing Reflection Beam: an open-weight model for agentic coding on AWSAWS Machine Learning · October 16, 2026
- Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation PipelineHugging Face · October 16, 2026