amazon-polly-generative

amazon-polly-generative is a skill for Claude Code, Codex from seandkendall/kiro-config. It costs 24 tokens per session (1,597 once invoked), scanned A, original, Apache-2.0.

A reference guide for Amazon Polly's Generative engine, a cloud service that turns written text into spoken audio. It lists supported voices and shows Python examples using SSML, a markup format for controlling speech delivery.

In plain words
What is it for?
Use it to generate MP3 speech with Amazon Polly, select an English voice, control rate, pitch, and pauses with SSML, and store the resulting audio in S3.
Why use it?
It helps developers choose a voice and configure more natural-sounding podcast or conversational speech. The examples show how to synthesize audio and stream it to Amazon S3.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to generate MP3 speech with Amazon Polly, select an English voice, control rate, pitch, and pauses with SSML, and store the resulting audio in S3.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seandkendall/kiro-config/amazon-polly-generative
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add seandkendall/kiro-config --skill amazon-polly-generative
Clone the repo
git clone --depth 1 https://github.com/seandkendall/kiro-config

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for amazon-polly-generative

README.md
[![agentmods](https://agentmods.dev/badge/skills/seandkendall/kiro-config/amazon-polly-generative/github.svg)](https://agentmods.dev/skills/seandkendall/kiro-config/amazon-polly-generative)
Your own site
<a href="https://agentmods.dev/skills/seandkendall/kiro-config/amazon-polly-generative"><img src="https://agentmods.dev/badge/skills/seandkendall/kiro-config/amazon-polly-generative/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for amazon-polly-generative

Your own site · 80×15
<a href="https://agentmods.dev/skills/seandkendall/kiro-config/amazon-polly-generative"><img src="https://agentmods.dev/badge/skills/seandkendall/kiro-config/amazon-polly-generative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,597 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01597
Opus 5 $0.00012 $0.00798
Sonnet 5 $0.00005 $0.00319
Haiku 4.5 $0.00002 $0.00160

Measured 10d ago against content hash 51ebb425fc31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

amazon-polly-generative scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/amazon-polly-generative/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amazon Polly Generative Voices

Overview

Amazon Polly Generative engine produces the most human-like speech synthesis available on AWS. Use it for podcast-style content where naturalness, expressiveness, and conversational flow are critical.

Available Generative Voices

Voice ID Gender Language Best For
Matthew Male en-US Conversational, energetic host
Ruth Female en-US Warm, articulate host
Stephen Male en-US Authoritative, documentary
Gregory Male en-US Calm, educational
Danielle Female en-US Professional, clear

API Usage (boto3)

import boto3

polly = boto3.client('polly', region_name='us-east-1')

response = polly.synthesize_speech(
    Engine='generative',
    OutputFormat='mp3',
    SampleRate='24000',
    Text='<speak>Hello from the road!</speak>',
    TextType='ssml',
    VoiceId='Matthew'
)

# Stream audio to S3
audio_stream = response['AudioStream'].read()

SSML for Natural Speech

Basic Structure

<speak>
  <prosody rate="medium" pitch="medium">
    Welcome back to the show!
  </prosody>
  <break time="500ms"/>
  <prosody rate="slow" pitch="low">
    Did you know that this highway was built in 1952?
  </prosody>
</speak>

Emphasis and Emotion

<speak>
  <emphasis level="strong">Wow</emphasis>, that's incredible!
  <break time="300ms"/>
  <prosody rate="fast" pitch="high">
    I can't believe we're already passing through Banff!
  </prosody>
</speak>

Pauses and Pacing

<!-- Between speakers (natural conversation pause) -->
<break time="800ms"/>

<!-- Dramatic pause -->
<break time="1500ms"/>

<!-- Quick interjection pause -->
<break time="200ms"/>

<!-- Paragraph break -->
<break strength="x-strong"/>

Whispering / Soft Speech

<amazon:effect name="soft">
  This is a little-known secret about this town...
</amazon:effect>

Read the full file on GitHub · 218 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 218 lines · 24 tokens per session scan A 51ebb425fc31

Subscribe to this mod's changes

amazon-polly-generative is a skill published in the GitHub repository seandkendall/kiro-config (8 stars, last pushed 12d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,597 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.