# X.AI Text-to-Speech (xona-agent, Base Mainnet)

> X.AI Text-to-Speech (xona-agent, Base Mainnet) is a paid API for AI agents from api.xona-agent.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-02).

Converts input text to spoken audio (MP3) using X.AI voices, payable via USDC on Base Mainnet.

## Facts

- Endpoint: POST https://api.xona-agent.com/base-main/audio/x-text-to-speech?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 1
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x-ai-text-to-speech-xona-agent-base-mainnet-87c1ddd8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_T0_rSRfWvn7_epUYgHRk8

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 x-ai-text-to-speech-xona-agent-base-mainnet-87c1ddd8 -d '<json body>'
```

Example prompt: Convert this script to speech using the Eve voice: 'Welcome to our platform. We're glad you're here.' and give me the MP3.

## When to prefer this

Choose this endpoint when you need AI-powered text-to-speech with X.AI voices (Eve, Ara, Leo, Rex, Sal) and are operating on the Base blockchain with USDC micropayments. Ideal for agents building voice content, narrations, or audio from text in a pay-per-call on-chain model.

## Known failure modes

- Invalid voice_id value (must be Eve, Ara, Leo, Rex, or Sal) — returns validation error
- Text input missing or empty — returns bad request error
- Payment not completed or insufficient USDC balance — returns 402 Payment Required
- Unsupported output format parameters — returns codec/format error
- Text too long — may return length limit error

## How this service works

X.AI text-to-speech: convert text to speech (MP3) (Base Mainnet).

## Output

An MP3 audio file containing the synthesized speech of the provided text, spoken in the selected voice with optional audio format parameters applied.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to convert to speech"
  },
  "voice_id": {
   "type": "string",
   "description": "Voice: Eve, Ara, Leo, Rex, or Sal"
  },
  "output_format": {
   "type": "string",
   "description": "Optional: codec, sample_rate, bit_rate"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x-ai-text-to-speech-xona-agent-base-mainnet-87c1ddd8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.xona-agent.com](https://www.zero.xyz/host/api.xona-agent.com/llms.txt)