---
format: "aidr-story-markdown/v1"
id: "bf991ee95d0532f13c5baade693a0b6d8b1d9350db29f4720d4349d4d0ddb857"
canonical_url: "https://aidr.today/bf991ee9?lang=en"
title: "Speaker-labeled transcription with WhisperX on SageMaker AI"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-24T16:20:12.000Z"
category: "Infra"
topics: ["whisper","sagemaker","amazon","speech-recognition","chips","inference"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/speaker-labeled-transcription-with-whisperx-on-sagemaker-ai/"]
summary: "The AWS WhisperX Deep Learning Container packages Whisper, wav2vec2 forced alignment, and speaker diarization into a GPU-ready image. Learn how to deploy it to Amazon SageMaker AI real-time and asynchronous endpoints for word-level, speaker-labeled transcription, plus the production details that matter: the GPU AMI pin, scaling, and cost controls."
---

# Speaker\-labeled transcription with WhisperX on SageMaker AI

> [Open the canonical story](<https://aidr.today/bf991ee9?lang=en>)

**Published:** 2026-09-24T16:20:12.000Z
**Category:** Infra
**Topics:** whisper, sagemaker, amazon, speech\-recognition, chips, inference

## Summary

The AWS WhisperX Deep Learning Container packages Whisper, wav2vec2 forced alignment, and speaker diarization into a GPU\-ready image\. Learn how to deploy it to Amazon SageMaker AI real\-time and asynchronous endpoints for word\-level, speaker\-labeled transcription, plus the production details that matter: the GPU AMI pin, scaling, and cost controls\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/speaker-labeled-transcription-with-whisperx-on-sagemaker-ai/>)