amazon-transcribe
Use Amazon Transcribe for AWS-based speech-to-text production: batch S3 transcription, real-time streaming, captions/subtitles, diarization, channel identification, custom vocabularies, vocabulary filters, language identification, PII/PHI handling, toxicity detection, Call Analytics, Medical, and secure S3/IAM/KMS workflows.
Profile →npx skills add calesthio/generative-media-skills --skill amazon-transcribe --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Use this skill when an agent needs to plan, run, review, or troubleshoot Amazon Transcribe as a speech-to-text provider inside an AWS-controlled workflow. Treat Amazon Transcribe as an AWS custody option first: it is strongest when the media already belongs in S3, the organization needs IAM/KMS/CloudTrail governance, captions must be generated from batch files, or real-time transcripts must flow through AWS streaming endpoints.
How it works
- Identifies when to use batch transcription for files in S3 or streaming transcription for live audio; considers Call Analytics and Medical pathways for specialized outputs.
- Differentiates between batch input formats (AMR, FLAC, M4A, MP3, MP4, Ogg, WebM, WAV) and streaming formats (FLAC, Ogg Opus, PCM); notes lossless formats preferred where possible.
- Chooses between speaker labels (diarization) and channel identification based on media structure and workflow needs; provides guidance on when to map speaker labels to human names post-processing.
- Recommends using custom vocabularies, vocabulary filters, and language identification per language requirements and multi-language scenarios.
- Emphasizes output formats: batch transcripts as JSON, video subtitles as WebVTT or SubRip when requested.
- Includes production heuristics for audio normalization, QA source-of-truth handling, and separate editorial passes for non-speech information in subtitles.
- Addresses AWS custody, security, and permissions, including S3 input/output, encryption, IAM policies, and least-privilege guidance.
When to use it
Use when planning, running, reviewing, or troubleshooting Amazon Transcribe in AWS-controlled workflows, especially when media resides in S3 and governance (IAM/KMS/CloudTrail) is needed, or when batch captions or real-time streaming are required.
What it can touch
- S3 input/output for batch jobs
- TLS in transit and encryption at rest with S3/KMS
- IAM roles and policies for access to S3 and KMS (permissions examples include GetObject, ListBucket, PutObject, decrypt/encrypt/generate-data-key)
- CloudTrail logging and optional data-protection practices
Caveats
- Do not treat this as a generic transcription model ranking; compare accuracy, latency, cost, language coverage against actual jobs.
- For healthcare, call analytics, and sensitive audio, separate Medical/Call Analytics paths before choosing.
- Toxicity detection is available only for batch transcriptions in en-US and may require redaction interplay with PII redaction; use as a flagging layer with human review.
- AWS opt-out for AI-service content improvement is available via Organizations policy; consider policy before processing sensitive audio.
# Amazon Transcribe Use this skill when an agent needs to plan, run, review, or troubleshoot Amazon Transcribe as a speech-to-text provider inside an AWS-controlled workflow. Treat Amazon Transcribe as an AWS custody option first: it is strongest when the media already belongs in S3, the organization needs IAM/KMS/CloudTrail governance, captions must be generated from batch files, or real-time tra
What does the amazon-transcribe skill do?
Use Amazon Transcribe for AWS-based speech-to-text production: batch S3 transcription, real-time streaming, captions/subtitles, diarization, channel identification, custom vocabularies, vocabulary filters, language identification, PII/PHI handling, toxicity detection, Call Analytics, Medical, and secure S3/IAM/KMS workflows.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill amazon-transcribe --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.