# Agent Hub Text-to-Speech

> Agent Hub Text-to-Speech is a paid API for AI agents from agents.torbrooknews.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-13).

Converts up to 2000 characters of text into a natural-sounding WAV audio file in one of six supported languages.

## Facts

- Endpoint: GET https://agents.torbrooknews.com/v1/speak?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-hub-text-to-speech-977f7fd7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_P154D0dYjOpt6n89oDKD1

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-hub-text-to-speech-977f7fd7
```

Example prompt: Can you convert this announcement text into a spoken WAV recording in French? The text is: 'Bienvenue à notre conférence annuelle. Nous sommes ravis de vous accueillir ici aujourd'hui.'

## When to prefer this

Choose this endpoint when you need a pay-per-call, no-subscription text-to-speech service that returns a standard WAV file with no API key required. It is ideal for agents needing quick, one-off speech synthesis across six languages (English, Spanish, French, Chinese, Japanese, Korean) at low cost ($0.01/call) without committing to a dedicated TTS provider account.

## Known failure modes

- Text exceeds 2000 characters — request rejected or truncated
- Unsupported language code provided — error or fallback to default (en)
- Missing required 'text' query parameter — 400-level error
- Network timeout if the TTS backend is slow to respond
- Empty or whitespace-only text input may return silence or error

## How this service works

Text to speech. Send up to 2000 characters and a language (en, es, fr, zh, jp, kr); get a natural-sounding WAV recording back. Also callable as GET with the same fields as query parameters.

## Output

A WAV audio file containing natural-sounding speech of the submitted text in the requested language. The binary audio data is returned directly and can be played or saved as a .wav file.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "lang": {
       "type": "string",
       "description": "en | es | fr | zh | jp | kr (default en)"
      },
      "text": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-hub-text-to-speech-977f7fd7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.torbrooknews.com](https://www.zero.xyz/host/agents.torbrooknews.com/llms.txt)