ToolVet
75trust / 100

Speech Transcribe

by dt0ur.online in AI models & inference

x402 APIPassing, checked 4 h ago

Transcribes spoken audio streams into timestamped English text using embedded Whisper neural speech recognition models.

POST
https://dt0ur.online/api/speech/transcribe
Price
$0.2
per call in USDC
Uptime
100%
last 30 days
Response time
344 ms
467 ms slowest 5%
Last check
Passed
4 h ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to call it

POST https://dt0ur.online/api/speech/transcribe

Each call costs $0.2 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://dt0ur.online/api/speech/transcribe
content-type: application/json

{
  "audio_url": "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav"
}

Parameters

ParameterTypeRequiredDescription
audio_urlstringYesPublic URL or file:// URI to a WAV (PCM) audio file. Only WAV is decoded; other formats (OGG, MP3, ...) fail with a 500.

Example response

The provider's example. We can't check it without paying.

{
  "model_used": "whisper-tiny.en",
  "status": "success",
  "transcription": " And so my fellow Americans ask not what your country can do for you, ask what you can do for your country."
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.2.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://dt0ur.online/api/speech/transcribe' \
  -H 'content-type: application/json' \
  --data-raw '{"audio_url":"https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav"}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://dt0ur.online/api/speech/transcribe' \
  -H 'content-type: application/json' \
  --data-raw '{"audio_url":"https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav"}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.2 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.2" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.2 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fdt0ur.online%2Fapi%2Fspeech%2Ftranscribe&method=POST
const res = await pay("https://dt0ur.online/api/speech/transcribe", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "audio_url": "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav"
  }),
});
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.2 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.2"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://dt0ur.online/api/speech/transcribe",
        json={
            "audio_url": "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav",
        },
    )
    print(res.status_code, res.text)

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
4 h agoPassed402440 ms$0.2
9 h agoPassed402304 ms$0.2
14 h agoPassed402285 ms$0.2
19 h agoPassed402461 ms$0.2
23 h agoPassed402284 ms$0.2
Show 10 older checks
28 h agoPassed402281 ms$0.2
33 h agoPassed402362 ms$0.2
37 h agoPassed402347 ms$0.2
41 h agoPassed402416 ms$0.2
45 h agoPassed402349 ms$0.2
2 days agoPassed402428 ms$0.2
2 days agoPassed402421 ms$0.2
2 days agoPassed402303 ms$0.2
3 days agoPassed402325 ms$0.2
3 days agoPassed402371 ms$0.2