# AgentRXI Text-to-Speech (MeloTTS)

> AgentRXI Text-to-Speech (MeloTTS) is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-15).

Converts text to spoken audio using MeloTTS, returning a WAV file with support for English, Spanish, French, Chinese, Japanese, and Korean.

## Facts

- Endpoint: GET https://agentrxi.com/v1/audio/speech?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-text-to-speech-melotts-0fad55ff
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wUr_51f1uwrwHtlWPv3kV

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 agentrxi-text-to-speech-melotts-0fad55ff
```

Example prompt: Can you turn this sentence into spoken audio in French: 'Bonjour, comment puis-je vous aider aujourd'hui?' — just give me back the WAV file.

## When to prefer this

Choose this endpoint when you need a simple, flat-rate, no-API-key text-to-speech solution with multilingual support (en, es, fr, zh, jp, kr) and OpenAI-compatible request shape. Ideal for agents already familiar with the OpenAI /v1/audio/speech interface who want a pay-per-call alternative without subscription overhead. Best for short-to-medium texts up to 2000 characters.

## Known failure modes

- Input text exceeds 2000 characters — request rejected
- Unsupported language code provided — may default to English or return an error
- Empty input text — likely returns an error or empty audio
- Network timeout for very long synthesis requests
- Payment failure (x402) if USDC payment is not properly submitted

## How this service works

OpenAI-compatible text to speech (MeloTTS): same request shape as OpenAI /v1/audio/speech (input, voice, model); returns a WAV file. Languages en, es, fr, zh, jp, kr via language. Up to 2000 characters, flat price, no API key. Also callable as GET with the same fields as query parameters.

## Output

A WAV audio file containing the synthesized speech for the provided text input in the specified language, ready for playback or downstream audio processing.

## 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": [
      "input"
     ],
     "properties": {
      "input": {
       "type": "string"
      },
      "model": {
       "type": "string",
       "description": "Ignored"
      },
      "voice": {
       "type": "string",
       "description": "Ignored"
      },
      "language": {
       "type": "string",
       "description": "en (default) | es | fr | zh | jp | kr"
      }
     }
    }
   },
   "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/agentrxi-text-to-speech-melotts-0fad55ff/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)