Tutorials
Cost-effective multilingual audio transcription at scale with Parakeet-TDT and AWS Batch
In this post, we walk through building a scalable, event-driven transcription pipeline that automatically processes audio files uploaded to Amazon Simple Storage Service (Amazon S3), and show you how
In this post, we walk through building a scalable, event-driven transcription pipeline that automatically processes audio files uploaded to Amazon Simple Storage Service (Amazon S3), and show you how to use Amazon EC2 Spot Instances and buffered streaming inference to further reduce costs.
Related
- Building intelligent audio search with Amazon Nova Embeddings: A deep dive into semantic audio understanding
- Power video semantic search with Amazon Nova Multimodal Embeddings
- Manage AI costs with Amazon Bedrock Projects
- How Guidesly built AI-generated trip reports for outdoor guides on AWS
Source: AWS ML Blog | 2026-04-22