# x402 AI Tools – Text-to-Speech (Amazon Polly)

> x402 AI Tools – Text-to-Speech (Amazon Polly) is a paid API for AI agents from ai.kagurazaka.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-30).

Converts text to speech using Amazon Polly and returns a signed URL to the audio file, valid for one hour.

## Facts

- Endpoint: POST https://ai.kagurazaka.dev/v1/speech?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-ai-tools-text-to-speech-amazon-polly-f59f5d7d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_i1C-PqVV7c-MyrzJLKkzC

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability x402-ai-tools-text-to-speech-amazon-polly-f59f5d7d -d '<json body>'
```

Example prompt: Read this paragraph aloud using the Matthew neural voice and give me an mp3 link: 'Welcome to our annual product showcase, where we highlight the most exciting innovations of the year.'

## When to prefer this

Choose this endpoint when you need quick, pay-per-call text-to-speech synthesis via Amazon Polly without managing AWS credentials or infrastructure. It is ideal for agents that occasionally need audio output in one of ~60 supported voices across multiple languages, and want a ready-to-use signed URL rather than raw audio bytes. Prefer alternatives if you need very long documents, real-time streaming audio, or custom SSML control beyond what Polly's standard API provides.

## Known failure modes

- Text exceeds 3000 characters for standard voices or 1000 for neural voices — request rejected
- Requested voice ID does not exist or is misspelled — error returned
- Requested voice does not support the chosen engine (e.g. neural not available for all voices) — error returned
- Signed URL expires after one hour — audio becomes inaccessible
- Payment of $0.02 USDC not completed — endpoint returns 402 Payment Required
- Unsupported format requested — only mp3 and ogg are valid

## How this service works

Turns text into speech with Amazon Polly and returns a signed URL of the audio, valid for an hour. Up to 3000 characters with standard voices or 1000 with neural ones. Voices include Joanna, Matthew (English), Mizuki, Takumi (Japanese), Lucia (Spanish), Lea (French), Vicki (German) and about 60 more.

## Output

A signed HTTPS URL pointing to the generated audio file (mp3 or ogg) hosted on Amazon S3, valid for one hour. The audio contains the synthesized speech rendered by the specified Polly voice and engine.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "the text, up to 3000 characters (standard) or 1000 (neural)"
  },
  "voice": {
   "type": "string",
   "description": "Polly voice id (default Joanna)"
  },
  "engine": {
   "enum": [
    "standard",
    "neural"
   ],
   "type": "string",
   "description": "default standard; not every voice has both"
  },
  "format": {
   "enum": [
    "mp3",
    "ogg"
   ],
   "type": "string",
   "description": "default mp3"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-ai-tools-text-to-speech-amazon-polly-f59f5d7d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ai.kagurazaka.dev](https://www.zero.xyz/host/ai.kagurazaka.dev/llms.txt)