80trust / 100

Audio Speech

by OpenAI text to speech in AI models & inference

x402 APIPassing, checked 3 h ago

OpenAI text to speech (gpt-4o-mini-tts, tts-1, tts-1-hd), paid per call in USDC. OpenAI list $15 / $30 per 1M characters (tts-1 / tts-1-hd) or $12 per 1M audio tokens (gpt-4o-mini-tts, quoted at 4 per character), plus $0.0005 (Base) or $0.0005 (Solana) per call; up to 4096 characters. Standard OpenAI body (input, voice, response_format, speed). Returns the audio bytes. One endpoint per model: /x402/v1/models/<key>/audio/speech. Rates: https://openai.mm.family/x402/pricing

POST https://openai.mm.family/x402/v1/audio/speech

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
30 ms typical, 99 ms slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://openai.mm.family/x402/v1/audio/speech" \
  -H "content-type: application/json" \
  -d '{"input":"Say hello","model":"gpt-4o-mini-tts","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%2Fopenai.mm.family%2Fx402%2Fv1%2Faudio%2Fspeech
const res = await pay("https://openai.mm.family/x402/v1/audio/speech", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"input":"Say hello","model":"gpt-4o-mini-tts","voice":"alloy"}),
});
console.log(await res.json());

Example input

{
  "input": "Say hello",
  "model": "gpt-4o-mini-tts",
  "voice": "alloy"
}

Example output

{
  "body": "binary audio bytes (mp3 by default)",
  "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
3 h agoPassed402109 ms$0.001
6 h agoPassed40230 ms$0.001
10 h agoPassed40299 ms$0.001
14 h agoPassed40290 ms$0.001
17 h agoPassed40228 ms$0.001
22 h agoPassed40298 ms$0.001
25 h agoPassed40230 ms$0.001
28 h agoPassed40230 ms$0.001
33 h agoPassed40228 ms$0.001