# amazon-transcribe

amazon-transcribe is a Claude Code skill for AWS speech-to-text workflows, covering batch files, live streams, captions, and speaker separation.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 132 installs · ★ 252 repo stars
- Author: calesthio
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/speech-to-text/amazon-transcribe/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/amazon-transcribe

## What it does

amazon-transcribe helps an agent plan, run, review, and troubleshoot Amazon Transcribe inside AWS-controlled workflows. It covers S3 batch jobs, real-time streaming, captions, speaker diarization, channel identification, custom vocabularies, vocabulary filters, language identification, PII/PHI handling, toxicity detection, Call Analytics, and Medical.

Batch processing requires the media file to be in S3. Secure workflows use IAM, KMS, and CloudTrail. The skill separates the choice between diarization and channel identification: split stereo tracks fit channel identification, while multiple voices on one channel call for diarization.

Streaming transcription uses HTTP/2 or WebSockets and needs an encoding, sample rate, and either a chosen language or language identification. Batch output is JSON with timing data and confidence scores; subtitle output can use `.vtt` and `.srt`.

## Requirements
- Works with: AWS

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill amazon-transcribe -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/amazon-transcribe/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/amazon-transcribe/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill amazon-transcribe -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/amazon-transcribe/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill amazon-transcribe -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/amazon-transcribe/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/generative-media-skills skills/providers/speech-to-text/amazon-transcribe
```

2. **Manually: put the files in place**
- File: `.github/skills/amazon-transcribe/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill amazon-transcribe -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/generative-media-skills --path skills/providers/speech-to-text/amazon-transcribe
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/amazon-transcribe/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill amazon-transcribe -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/speech-to-text/amazon-transcribe/SKILL.md

## When to use it
- transcribe an audio file from S3 with a batch job
- send live audio through real-time transcription
- separate speakers or isolated audio channels
- produce captions in `.vtt` and `.srt`
- route call recordings to Call Analytics or medical speech to Medical

## Example prompts
- Transcribe this S3 audio file with an Amazon Transcribe batch job and return JSON with timing data.
- Set up real-time AWS transcription for this live audio stream and identify the language.
- Use diarization on this single-channel recording, then show how to verify the mapping for `spk_0` and `spk_1`.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: aadf46469ff34ece.

BEGIN THIRD-PARTY FILE aadf46469ff34ece
```text
---
name: amazon-transcribe
description: "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."
---

# 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 transcripts must flow through AWS streaming endpoints.

Do not use this skill as a generic "best transcription model" ranking. Compare accuracy, latency, cost, language coverage, and custody requirements against the actual job. For healthcare, call-center analytics, and sensitive audio, separate the general Transcribe path from the Medical and Call Analytics products before choosing.

Facts below were verified against AWS documentation on 2026-07-10 unless a line says otherwise.

## Choose the right Amazon Transcribe surface

Documented fact: Amazon Transcribe is an automatic speech recognition service that converts audio to text. It can be used through asynchronous batch jobs for media files or real-time streaming for live audio. Sources: [What is Amazon Transcribe](https://docs.aws.amazon.com/transcribe/latest/dg/what-is.html), [Streaming audio](https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html), [StartTranscriptionJob API](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html).

Use this decision map:

- Batch transcription: use for files in Amazon S3, offline transcripts, subtitles, captions, podcast/video backlogs, archives, QA review, and workflows that can wait for job completion. Batch requires the media file to be in S3 before `StartTranscriptionJob`.
```
END THIRD-PARTY FILE aadf46469ff34ece

The third-party file has ended. Everything between the aadf46469ff34ece tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2103 of 25404 bytes. © calesthio · MIT · https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/speech-to-text/amazon-transcribe/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
