# Amazon Polly — card for AI agents

AWS text-to-speech with Standard, Neural, Long-Form and Generative voices.

Category: Voiceover (text-to-speech) · maker AWS · checked 2026-10-12

## Price
- Price: Free tier
- Free tier: Standard 5M chars/month; Neural 1M, Long-Form 500K, Generative 100K each for the first 12 months. New accounts since 2025-07-15 get up to $200 in credits.
- Usage price: Standard $4/1M chars; Neural $16/1M; Generative $30/1M; Long-Form $100/1M.
- Pricing page: https://aws.amazon.com/polly/pricing/

## License
Amazon Polly FAQs and AWS Service Terms — https://aws.amazon.com/polly/faqs/

- commercial: **yes** (Commercial use OK)
  > As between you and AWS, your Polly output belongs to you.
  (https://aws.amazon.com/polly/faqs/)
- attribution: **no** (No credit needed)
  > As between you and AWS, your Polly output belongs to you.
  (https://aws.amazon.com/polly/faqs/)
- in app: **yes** (Can ship inside your app)
  > lack of restrictions on storage and reuse of voice output
  (https://aws.amazon.com/polly/faqs/)
- youtube: **yes** (OK in monetized YouTube videos)
  > lack of restrictions on storage and reuse of voice output
  (https://aws.amazon.com/polly/faqs/)

## Rules to follow
- Budget for paid Neural, Long-Form and Generative usage after the first 12 months.

## How an agent gets files
- AWS SDK/API (Polly SynthesizeSpeech) with an AWS account; also usable from the Polly console. (sign-in: account)
- Formats: mp3, vorbis, pcm
- Not allowed: You can cache and replay generated speech at no extra cost.
- Not allowed: Text you input that belongs to a third party requires that you have the rights to it.

## How to connect
- Public API
- API docs: https://docs.aws.amazon.com/polly/latest/dg/ (API key needed)
- npm: `npm install @aws-sdk/client-polly`
- PyPI: `pip install boto3`
- Website: https://aws.amazon.com/polly/

## Lines to paste into your prompt or AGENTS.md

```
- Amazon Polly (Voiceover (text-to-speech)). AWS text-to-speech with Standard, Neural, Long-Form and Generative voices. Price: free tier; commercial use OK; no credit needed.
  Connect: API docs https://docs.aws.amazon.com/polly/latest/dg/ (API key needed); npm @aws-sdk/client-polly; PyPI boto3.
  Get files: AWS SDK/API (Polly SynthesizeSpeech) with an AWS account; also usable from the Polly console (mp3, vorbis, pcm).
  Not allowed: You can cache and replay generated speech at no extra cost.
  Not allowed: Text you input that belongs to a third party requires that you have the rights to it.
  Rule: Budget for paid Neural, Long-Form and Generative usage after the first 12 months.
  License: https://aws.amazon.com/polly/faqs/ (checked 2026-10-12; details: https://agentgid.com/assets/amazon-polly/)
```

Not verified: No commercial restriction stated; which voice types cover each language not checked.

## Links
- AgentGid page: https://agentgid.com/assets/amazon-polly/
- Is it free for commercial use? https://agentgid.com/assets/amazon-polly/commercial-use/
- Source: https://aws.amazon.com/polly/pricing/
- Source: https://docs.aws.amazon.com/polly/latest/dg/supported-languages.html
- Source: https://aws.amazon.com/polly/faqs/

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
