ToolVet
71trust / 100

Audio Translate Speech

by Tanod mlpeek in AI models & inference

x402 APIPassing, checked 2 h ago

mlpeek (Tanod) speech translation: an audio file of up to 2 minutes as translated text in English or 14 languages with timed segments, optionally spoken (Whisper, Argos, Kokoro). Use when an agent must turn speech in another language into translated text or spoken audio, from a 2-minute clip.

POST https://tanod.dev/v1/audio/translate-speech

Last 30 days

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

Uptime
100%
Response time
1.0 s typical, 1.0 s slowest 5%
Last check
2 h ago
Next check
any minute now

How to call it

POST https://tanod.dev/v1/audio/translate-speech

Each call costs $0.02 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://tanod.dev/v1/audio/translate-speech
content-type: application/json

{
  "target": "es",
  "url": "https://tanod.dev/samples/speech-sample.mp3"
}

Parameters

ParameterTypeRequiredDescription
file_base64string or nullNoThe audio file as base64 (at most 25 MB decoded); or use url. At most 2 minutes (45 seconds with speak). Default: null.
formatstringNoWith speak: mp3, wav or ogg. One of: mp3, wav, ogg. Default: "mp3".
include_transcriptbooleanNotrue adds `transcript` in the spoken language with a second Whisper pass (about doubles the speech-to-text time). English audio always returns it. Default: false.
languagestring or nullNoOptional spoken language as an ISO 639-1 code. Default: detected. Default: null.
outputstringNobase64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window. One of: base64, url. Default: "base64".
speakbooleanNotrue adds `audio`, the translation spoken (Kokoro). Targets en, es, fr, hi, it and pt only; the clip is limited to 45 seconds and at most 800 characters are spoken. Default: false.
targetstringYesLanguage of the translation: en (one Whisper pass) or es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id, tl (Whisper to English, then English to the target). One of: en, es, fr, de, pt, it, nl, ru, zh, ja, ko, ar.
urlstring or nullNoPublic http(s) URL of the audio file (at most 25 MB; private, internal and IP-literal hosts are refused); or use file_base64. Default: null.
voicestring or nullNoWith speak: a voice for the target language (default af_heart en, ef_dora es, ff_siwis fr, hf_alpha hi, if_sara it, pf_dora pt). Default: null.

Example response

The listing has no example response.

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.02.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://tanod.dev/v1/audio/translate-speech' \
  -H 'content-type: application/json' \
  --data-raw '{"target":"es","url":"https://tanod.dev/samples/speech-sample.mp3"}'

# 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://tanod.dev/v1/audio/translate-speech' \
  -H 'content-type: application/json' \
  --data-raw '{"target":"es","url":"https://tanod.dev/samples/speech-sample.mp3"}' \
  | 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 $0.02 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.02" });
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 $0.02 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Ftanod.dev%2Fv1%2Faudio%2Ftranslate-speech&method=POST
const res = await pay("https://tanod.dev/v1/audio/translate-speech", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "target": "es",
    "url": "https://tanod.dev/samples/speech-sample.mp3"
  }),
});
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 $0.02 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.02"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://tanod.dev/v1/audio/translate-speech",
        json={
            "target": "es",
            "url": "https://tanod.dev/samples/speech-sample.mp3",
        },
    )
    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
2 h agoPassed4021.1 s$0.02
6 h agoPassed4021.0 s$0.02
15 h agoPassed402270 ms$0.02