xai · Audio

xAI Text-to-Speech

Audio model · Available upstream

Expressive text-to-speech with over two dozen voices, speech tags, and multilingual support

API documentation View pricing

Generation is available through the published Meldport configurations below. Review the exact quote before submitting.

Model ID: xai-tts
Released: Mar 16, 2026
Billing unit: Characters

Meldport generation prices

xAI Text-to-Speech

API configuration IDbac25196-04de-443f-8b1a-993b507a9c2c

text to audio

Text rateMeldport $0.018/ 1K characters

Final quote depends on text length. Check the exact quote before generating.

Variable billing details

API request and parameters

Use audio:generate on your API key. This configuration runs text to audio and returns audio/mpeg.

This configuration does not require an uploaded image. Choose a different configuration ID to change the workflow or output settings. Send only options listed below.

allowed_optionsJSON

{
  "voice": {
    "enum": [
      "carina",
      "zagan",
      "helix",
      "orion",
      "luna",
      "iris",
      "altair",
      "zenith",
      "perseus",
      "helios",
      "lux",
      "kepler",
      "rigel",
      "cosmo",
      "celeste",
      "ursa",
      "sirius",
      "lumen",
      "castor",
      "naksh",
      "atlas",
      "una",
      "ara",
      "eve",
      "leo",
      "rex",
      "sal"
    ],
    "type": "string",
    "required": true,
    "maxLength": 100
  },
  "language": {
    "enum": [
      "en",
      "ar-EG",
      "ar-SA",
      "ar-AE",
      "bn",
      "zh",
      "fr",
      "de",
      "hi",
      "id",
      "it",
      "ja",
      "ko",
      "pt-BR",
      "pt-PT",
      "ru",
      "es-MX",
      "es-ES",
      "tr",
      "vi"
    ],
    "type": "string",
    "required": false,
    "maxLength": 10
  }
}

Replace the prompt and set a unique MELDPORT_IDEMPOTENCY_KEY for this operation. The example quotes the request and then creates one paid job. Read the billing rules before accepting variable charges.

generate.mjsJavaScript

const api = "https://api.meldport.com";
const key = process.env.MELDPORT_API_KEY;
const idempotencyKey = process.env.MELDPORT_IDEMPOTENCY_KEY;
if (!key || !idempotencyKey) throw new Error("Set your API key and a unique operation ID first.");

async function post(path, body) {
  const response = await fetch(api + path, {method: "POST",
    headers: {Authorization: `Bearer ${key}`, "Content-Type": "application/json"},
    body: JSON.stringify(body)});
  const result = await response.json();
  if (!response.ok) throw new Error(JSON.stringify(result.error));
  return result;
}

const request = {
  "configuration_id": "bac25196-04de-443f-8b1a-993b507a9c2c",
  "prompt": "Replace with your prompt or speech script.",
  "options": {
    "voice": "carina"
  },
  "input_asset_ids": []
};
const {data: quote} = await post("/v1/media/quotes", request);
console.log("Quote:", quote);
const result = await post("/v1/media/jobs", {
  ...request, idempotency_key: idempotencyKey,
  accepted_customer_price_microusd: quote.customer_price_microusd,
  accepted_maximum_reservation_microusd: quote.maximum_reservation_microusd,
  ...(quote.billing_policy_version === "actual-cost-v1"
    ? {billing_policy_version: "actual-cost-v1"} : {}),
});
console.log(result.job);
// Poll GET /v1/media/jobs/<job.id> with the same API key.
// Keep this operation ID for retries. A new ID requests another generation.

Poll the returned job ID. Download only after state is succeeded and billing_state is settled. Polling and download example.

About this model

xAI Text-to-Speech converts text into natural-sounding spoken audio with a single API call. It offers more than two dozen expressive voices, inline speech tags for fine-grained control over pauses, laughter, whispers, and emphasis, and supports over 20 auto-detected languages.

text to audio
checkpoint