Text-to-speech (OpenAI-compatible)

OpenAI-compatible text-to-speech over x402 - point any OpenAI SDK's audio.speech.create() at base_url https://agent402.tools/v1 and pay $0.06 per call in USDC, no API key, no signup. Send POST /v1/audio/speech with the required field input and pay $0.060 per call over x402 or MPP (there is no free tier). It returns raw bytes, not JSON, with Content-Type audio/mpeg or audio/pcm.

Served by Voxtral Mini TTS behind a five-model failover chain (xAI Grok Voice, Kokoro, MAI-Voice-2 Flash, MAI-Voice-2), every link proven by a real paid canary - a provider outage never becomes your failure. Up to 2,000 chars in, raw mp3 (default) or pcm bytes out - the same wire shape as OpenAI's endpoint. OpenAI voice names (alloy, nova, …) map per-model; native voice ids (e.g. en_paul_cheerful) work too. zdr:true routes only to zero-data-retention providers.

Category: LLM gateway · Tags: tts text-to-speech speech audio voice llm ai inference

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{"input":"Agent402 serves fourteen hundred tools, paid per call.","voice":"alloy"}'

Without payment this returns HTTP 402 Payment Required with the exact price for v1-audio-speech; any x402 v2 or MPP client pays it and retries.

Example response

A 200 carries raw bytes, not JSON, with Content-Type audio/mpeg or audio/pcm: the file itself.

From an MCP client

catalog.call {
  "slug": "v1-audio-speech",
  "params": {
    "input": "Agent402 serves fourteen hundred tools, paid per call.",
    "voice": "alloy"
  }
}

The hosted connector at https://agent402.tools/mcp needs a payment for v1-audio-speech; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.

Errors and behavior

• input is required. An input the tool rejects returns an HTTP 4xx whose body carries error, tool, expected, required and example, so the caller can correct it.
• A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
• Wallet-only: this tool runs a model, so it has no proof-of-work tier. A prepaid card-credits key issued earlier (Authorization: Bearer a402_...) also pays it.
• Model-backed: the answer is generated by a model, so the same input can produce different wording.
• A GET or HEAD to /v1/audio/speech returns the same 402 quote, so the price can be read without a body.
• An Idempotency-Key header does not replay this tool's answer: the replay cache holds JSON answers only, so a retried paid call runs and is charged again.

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/v1/audio/speech", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": "Agent402 serves fourteen hundred tools, paid per call.",
    "voice": "alloy"
  }),
});

Related tools