78trust / 100

Audio Speech

by Text-to-speech in AI models & inference

x402 APIPassing, checked 1 h ago

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. 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.

POST https://agent402.tools/v1/audio/speech

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
283 ms typical, 319 ms slowest 5%
Last check
1 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
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"}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagent402.tools%2Fv1%2Faudio%2Fspeech
const res = await pay("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"}),
});
console.log(await res.json());

Example input

{
  "input": "Agent402 serves fourteen hundred tools, paid per call.",
  "voice": "alloy"
}

Example output

"(raw mp3 bytes - Content-Type: audio/mpeg)"

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
1 h agoPassed402190 ms$0.06
5 h agoPassed402272 ms$0.06
9 h agoPassed402314 ms$0.06
12 h agoPassed402283 ms$0.06
16 h agoPassed402268 ms$0.06
19 h agoPassed402315 ms$0.06
23 h agoPassed402432 ms$0.06
27 h agoPassed402316 ms$0.06
30 h agoPassed402319 ms$0.06
34 h agoPassed402316 ms$0.06
37 h agoPassed402273 ms$0.06
43 h agoPassed402258 ms$0.06