Deepgram ports Nova-3 speech model to AWS Trainium2
What happened
On 20 October 2026, the AWS Machine Learning Blog published a first-hand report that Deepgram worked with AWS to port its Nova-3 speech-to-text model to Trainium2 chips, for offline batch workloads such as contact-centre analytics and medical transcription. The final configuration runs eight model replicas on a single Amazon EC2 trn2.3xlarge instance, processing 11%–70% more audio per dollar than the previous compute setup. Earlier coverage did not include the specific configuration or performance figures; this is the latest development.
Written by AI from the reports · updated 2 h ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogHow Deepgram optimized voice AI at scale with AWS Trainium
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.
Heat of this event
Not enough continuous observations yet to draw a trend.