# Amazon — How Deepgram optimized voice AI at scale with AWS Trainium

- Company: Amazon (amazon.com)
- Announced: 2026-10-19T16:23:22+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/how-deepgram-optimized-voice-ai-at-scale-with-aws-trainium/
- Record: https://forck.live/items/24664-how-deepgram-optimized-voice-ai-at-scale-with-aws-trainium
- Subject: Bedrock / Nova
- Models affected: Nova-3

Deepgram worked with AWS to port its Nova-3 speech-to-text model to AWS Trainium2 for offline batch workloads such as contact-center analytics and medical transcription. The engagement began with Nova-3 as standard PyTorch code, and over several months the two teams moved it to Trainium2 in PyTorch reconstruction and tuned it for the new hardware. The final configuration runs eight model replicas on a single Amazon EC2 trn2.3xlarge instance, and on Deepgram's offline, throughput-oriented batch workloads it processed 11–70 percent more audio per dollar than the compute options Deepgram had been running, measured using instance pricing at the time of the evaluation. Deepgram says the gains help it scale efficiently, keep shipping better models, and bring them to customers at lower prices, and that the benefits can extend to customers who self-host Deepgram models in their own VPC on Amazon SageMaker AI. The port used TorchNeuron, the native PyTorch integration of the Neuron Compiler, and the compiled path ran every model operation on Trainium2 with no CPU fallbacks detected. Deepgram replaced several layers with fused kernels from the public NKI Library and built a data-parallel Rust runtime so the model could run without Python or PyTorch in the serving path.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/how-deepgram-optimized-voice-ai-at-scale-with-aws-trainium/:

> The final configuration runs eight model replicas on a single Amazon Elastic Compute Cloud (Amazon EC2) trn2.3xlarge instance. On Deepgram’s offline, throughput-oriented batch workloads, that setup processed 11–70 percent more audio per dollar than the compute options Deepgram had been running.

---

Record: https://forck.live/items/24664-how-deepgram-optimized-voice-ai-at-scale-with-aws-trainium
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md