---
format: "aidr-story-markdown/v1"
id: "091099d846f62db2245852ad7e00e99d780a09b15ee5d7bfda73e405153e5189"
canonical_url: "https://aidr.today/091099d8?lang=en"
title: "Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-13T19:35:35.000Z"
category: "Data"
topics: ["amazon","inference","data-engineering"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/cost-optimizing-assemblyai-speech-to-text-inference-on-aws-with-amazon-ec2-spot/"]
summary: "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. This setup achieves 70% cost savings while maintaining SLA commitments across European Regions."
---

# Cost\-optimizing AssemblyAI speech\-to\-text inference on AWS with Amazon EC2 Spot

> [Open the canonical story](<https://aidr.today/091099d8?lang=en>)

**Published:** 2026-11-13T19:35:35.000Z
**Category:** Data
**Topics:** amazon, inference, data\-engineering

## Summary

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\. This setup achieves 70% cost savings while maintaining SLA commitments across European Regions\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/cost-optimizing-assemblyai-speech-to-text-inference-on-aws-with-amazon-ec2-spot/>)