DigestAI news desk

Cut through the AI noise.

Enterprise & Industry8 min read

AWS adds WhisperX to SageMaker for speaker-labeled audio transcription

AWS released a WhisperX-based deep learning container for Amazon SageMaker that adds speaker diarization and per-word timestamps to OpenAI’s Whisper model. The container supports real-time (60-second cap) and asynchronous (unlimited duration) endpoints, with outputs in JSON, SRT, or VTT formats. It handles contact-center calls, legal depositions, and media transcripts, enabling compliance…

1 source primary source

Key points

  • WhisperX container adds speaker labels and per-word timestamps to OpenAI’s Whisper model for SageMaker
  • Supports real-time (60s cap) and async endpoints with S3 integration for long audio processing
  • Outputs in JSON, SRT, or VTT formats; requires GPU instances and S3 buckets for async workflows

The solution requires GPU instances (e.g., ml.g4dn.xlarge or ml.g5.2xlarge) and S3 buckets for async workflows. AWS provides a JupyterLab notebook for deployment, with best practices like AMI pinning, autoscaling, and S3 security. The container is pre-configured with Whisper, wav2vec2 alignment, and diarization weights, eliminating the need for manual model setup.

Full story from AWS Machine Learning Blog · by Ayush Sharma primary sourceOpen source ↗

Speaker-labeled transcription with WhisperX on SageMaker AI

AWS Machine Learning Blog · 24 September 2026

Loading the full article…

This text was published by AWS Machine Learning Blog and written by Ayush Sharma. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
AWSOpenAIWhisperWhisperXwav2vec2

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories