# ADH Text-to-Speech (TTS) — agentdatum.com

> ADH Text-to-Speech (TTS) — agentdatum.com is a paid API for AI agents from agentdatum.com, paid per call via x402, $0.01/call, status down (last checked 2026-11-20).

Converts text to speech audio using a configurable voice, returning a base64-encoded MP3.

## Facts

- Endpoint: POST https://agentdatum.com/api/v1/tool/tool-tts?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: down
- Last checked: 2026-11-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/adh-text-to-speech-tts-agentdatum-com-4d1da0fc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3BdCSTl58wOdNppLA6YXD

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 adh-text-to-speech-tts-agentdatum-com-4d1da0fc -d '<json body>'
```

Example prompt: Can you read out the following sentence in the zh-Xiaoxiao voice and give me the audio as an MP3: 'Welcome to our platform, please proceed with your order.'

## When to prefer this

Choose this endpoint when you need fast, low-cost ($0.01 USDC) text-to-speech synthesis with a base64 MP3 response suitable for direct embedding, and you are already operating within the agentdatum.com x402 payment ecosystem. Particularly useful for Chinese-language voice synthesis (zh-Xiaoxiao).

## Known failure modes

- Empty or missing text parameter returns an error
- Unsupported voice name may fall back to default or return an error
- Very long text strings may be truncated or cause timeout
- Payment failure via x402 will block the request
- Base64 output may be large for long text inputs

## How this service works

ADH 金融情报层：把 239 个原始数据源洗成带实体解析、时间同步、溯源与派生结论的情报（宏观regime / 加密尽调 / 事件窗口），免费注入你的 AI 上下文。Agent 走 x402 结算，人类订阅（PayPal）即将上线。

## Output

A JSON object containing the voice identifier used (e.g. 'zh-Xiaoxiao') and a base64-encoded MP3 audio string ('audio_b64') representing the synthesized speech of the input text.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "voice": "zh-Xiaoxiao",
  "audio_b64": "<base64 mp3>"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/adh-text-to-speech-tts-agentdatum-com-4d1da0fc/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentdatum.com](https://www.zero.xyz/host/agentdatum.com/llms.txt)
