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…
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.
The story so far
3 episodes →- AWS adds WhisperX to SageMaker for speaker-labeled audio transcriptionthis story
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 ↗
Coverage and discussion
2sources- Deploying real-time personalized speech with Qwen3-TTS on Amazon SageMaker AIPrimary source · AWS Machine Learning Blog ·
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.
More in Enterprise & Industry
All →- Anthropic replaces Git with Scion after AI agents drive merges from 2,500 to 30,000 per day · 11 src
- Sullivan & Cromwell builds legal tool Agreement Analyzer with OpenAI · 1 src
- Opsin raises $21M to track enterprise AI agents and flag risky behavior · 1 src
- Microsoft adds deepfake detection to Teams in November 2026 · 1 src
- Access Construction launches agentic AI layer Evo for estimating, project management and ERP · 1 src
Comments
via GitHub Discussions