# Agent Factory TTS – Text-to-Speech via Amazon Polly

> Agent Factory TTS – Text-to-Speech via Amazon Polly is a paid API for AI agents from d1x8xrm7jrzkbs.cloudfront.net, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Converts text to speech audio using Amazon Polly neural voices, returning base64-encoded audio, billed per-request in USDC over the x402 protocol.

## Facts

- Endpoint: POST https://d1x8xrm7jrzkbs.cloudfront.net/v1/tts
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-factory-tts-text-to-speech-via-amazon-polly-5418f65a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_s6626NiMiyuU_ulvXnRDt

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 agent-factory-tts-text-to-speech-via-amazon-polly-5418f65a -d '<json body>'
```

Example prompt: Can you synthesize this paragraph into speech using the Joanna neural voice: 'Welcome to our weekly briefing. Here are the top stories for today.'

## When to prefer this

Choose this endpoint when you need pay-per-use neural text-to-speech synthesis without a subscription, especially when operating in a crypto-native or x402-payment-capable agent environment billed in USDC. Prefer it over traditional TTS APIs when your agent already handles x402 micropayments on Base and you want Amazon Polly neural voice quality at $0.02 per call with no upfront commitment.

## Known failure modes

- Missing required 'text' field returns a validation error
- Invalid or unsupported voice name may cause synthesis failure or fallback to default voice
- Very long text inputs may exceed service limits and return an error
- Payment failure over x402/USDC causes a 402 response before synthesis occurs
- Network or CloudFront timeout for unusually slow synthesis requests

## How this service works

Pay-per-request datasets and Amazon Bedrock inference for AI agents, settled in USDC over the x402 protocol on Base.

## Output

Returns a JSON object containing 'audioBase64' (a base64-encoded audio file of the synthesized speech) and 'contentType' (e.g. 'audio/mpeg') indicating the audio format. The agent can decode the base64 string to obtain a playable audio file.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to synthesize"
  },
  "voice": {
   "type": "string",
   "description": "Polly neural voice, e.g. Joanna"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audioBase64": {
   "type": "string"
  },
  "contentType": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-factory-tts-text-to-speech-via-amazon-polly-5418f65a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from d1x8xrm7jrzkbs.cloudfront.net](https://www.zero.xyz/host/d1x8xrm7jrzkbs.cloudfront.net/llms.txt)