What problem does it solve?
This Skill helps teams turn recorded or live audio into accurate, reviewable transcripts and captions while choosing the right Amazon Transcribe workflow, protecting sensitive data, and preparing media for publication or downstream analysis.
Core Features & Use Cases
- Batch and Streaming Transcription: Choose offline S3 transcription for finished media or low-latency streaming for live captions and voice workflows.
- Speaker and Caption Workflows: Apply channel identification, speaker diarization, SRT and VTT subtitles, custom vocabularies, and human QA for accessible deliverables.
- Specialized Processing: Evaluate Call Analytics for customer-agent insights, Transcribe Medical for healthcare speech, toxicity detection, language identification, and PII or PHI redaction.
- Secure AWS Operations: Plan customer-owned S3 storage, IAM least privilege, KMS encryption, CloudTrail logging, lifecycle deletion, regional constraints, quotas, and pricing.
- Use Case: For a finished webinar in S3, generate a speaker-labeled transcript and public captions, then review names, timing, non-speech cues, and redaction before release while retaining raw media in private encrypted storage.
Quick Start
Use the amazon-transcribe skill to create a secure batch transcription and caption plan for the finished audio or video in my AWS S3 bucket, including speaker handling, vocabulary, redaction review, subtitles, and delivery QA.
