Skip to content

AssemblyAI cuts speech transcription inference costs with EC2 Spot

What happened

AI digest

On 14 November 2026, the AWS Machine Learning Blog reported that AssemblyAI runs speech-to-text inference on AWS using GPU clusters that combine Amazon ECS with EC2 Spot and On-Demand instances, absorbing Spot interruptions through an Amazon SQS queue retry mechanism to cut costs significantly while maintaining its SLA. The report did not disclose the specific cost reduction, cluster size or SLA metrics.

Written by AI from the reports · updated 2 d ago

Timeline

Follow the reports to see the event from each side.

Nov 14
  1. AWS Machine Learning Blog
    Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot

    Learn how AssemblyAI runs cost-optimized speech-to-text inference at scale on AWS, using Amazon ECS, Amazon EC2 Spot GPU instances, and an Amazon SQS-based retry architecture to achieve 70% cost savings while maintaining SLA commitments across European Regions.

Heat of this event

Current heat 3·Peak in the comparable range 9(Nov 14 07:00)·Change over 24 hours in the comparable range -51%

02.557.510Nov 1407:00Nov 1422:00Nov 1512:00Nov 1603:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.