# SiteCheck API Text-to-Speech

> SiteCheck API Text-to-Speech is a paid API for AI agents from api.sitecheck-api.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-02).

Converts text (up to 1000 characters) into an MP3 audio file using a choice of named voices, powered by Deepgram Aura-2, with pay-per-call billing via USDC on Base.

## Facts

- Endpoint: POST https://api.sitecheck-api.workers.dev/api/tts?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-api-text-to-speech-79f6f011
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LvEeXPTEXc8ENW4B1sz1m

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 sitecheck-api-text-to-speech-79f6f011 -d '<json body>'
```

Example prompt: Read this aloud using the 'luna' voice: 'Welcome to our quarterly product update — here's what we shipped this month.' Return the MP3 audio.

## When to prefer this

Choose this endpoint when you need quick, pay-per-call text-to-speech without any signup or API key setup, especially when operating in an agentic context that supports x402 micropayments on Base. It offers a wide selection of named voices and returns base64 MP3 audio suitable for embedding or playback. Prefer it over subscription-based TTS APIs when cost must be per-call and no authentication credential management is desired.

## Known failure modes

- Text exceeds 1000 character limit — request rejected or truncated
- Invalid voice name provided — may return error or fall back to default
- Payment failure via x402/USDC — 402 response, audio not returned
- Network timeout on Cloudflare Worker — 5xx error
- Empty text input — likely returns an error or silent audio

## How this service works

Pay-per-call tools for AI agents: image generation, speech-to-text, text-to-speech, embeddings, LLM chat, website audits and contact enrichment. Payment: x402, USDC on Base. No signup, no API key.

## Output

A JSON object containing the audio encoded as a base64 MP3 string (audio_base64), the MIME type (audio/mpeg), the model used (@cf/deepgram/aura-2-en), and the voice name selected. The agent must decode the base64 string to obtain the playable audio file.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Up to 1000 chars"
  },
  "voice": {
   "type": "string",
   "description": "luna, asteria, athena, helena, hera, aurora, orion, apollo, arcas, atlas, hermes, zeus, draco, odysseus"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "mime": "audio/mpeg",
  "model": "@cf/deepgram/aura-2-en",
  "voice": "luna",
  "audio_base64": "SUQzBAAAAAAA..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-api-text-to-speech-79f6f011/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.sitecheck-api.workers.dev](https://www.zero.xyz/host/api.sitecheck-api.workers.dev/llms.txt)