AssemblyAI Optimizes AWS Speech-to-Text Cost
The story so far
AssemblyAI optimized its speech-to-text inference cost on AWS by using a mix of EC2 On-Demand and Spot instances, and building a resilient architecture with Amazon ECS, SQS, and EventBridge, achieving cost reduction within the European AWS region and meeting the service level agreement (SLA). This aims to address the high cost issue of using only On-Demand instances, as Spot instances can provide significant savings, and EC2 can be reclaimed with a 2-minute warning when needed. AssemblyAI's API provides transcription, speaker detection, sentiment analysis, chapter detection, and PII anonymization services, and this architecture uses Amazon ECS, EC2 Spot instances, and SQS.
AI-written from the reports · Updated 22 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- AWS Machine Learning BlogHow AssemblyAI optimizes speech-to-text inference costs using EC2 Spot instances on AWS
AssemblyAI builds an elastic architecture on AWS by hybridly using EC2 On-Demand and Spot instances, and leveraging Amazon ECS, SQS, and EventBridge, to increase GPU instance utilization by 3.5 times, achieve cost reduction within the European AWS region, and meet service level agreements (SLA). Its inference platform is deployed on three GPU instance families: g4dn, g5, and g6.
Heat over time
- Now
- 5
- Peak
- 1014 Nov, 04:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.