ToolVet
78trust / 100

Transcribe

by Sift Web Tools in AI models & inference

x402 APIPassing, checked 2 h ago

Speech to text from an audio or video file URL (up to 5 minutes), with timestamps, SRT or VTT. Transcribes speech in an audio or video file (mp3, wav, m4a, mp4, webm and more; up to 80 MB and 5 minutes) with OpenAI Whisper running on our own servers. Auto-detects the language (99 languages). Returns text with segment timestamps, or ready-made SRT or VTT subtitles.

GET
https://sift.srv1996466.hstgr.cloud/v1/transcribe
Price
$0.02
per call in USDC
Uptime
94.1%
last 30 days
Response time
195 ms
315 ms slowest 5%
Last check
Passed
2 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

GET https://sift.srv1996466.hstgr.cloud/v1/transcribe

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.

GET https://sift.srv1996466.hstgr.cloud/v1/transcribe?url=https%3A%2F%2Fsift.srv1996466.hstgr.cloud%2Fsamples%2Fspeech.mp3

Parameters

ParameterTypeRequiredDescription
formatstringNojson, text, srt or vtt (default json)
languagestringNoTwo-letter language code, e.g. en (default auto-detect)
urlstringYesAudio or video file URL

Example response

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

{
  "duration_s": 4.1,
  "language": "en",
  "segments": [
    {
      "end": 3.2,
      "start": 0,
      "text": "The quick brown fox jumps over the lazy dog."
    }
  ],
  "text": "The quick brown fox jumps over the lazy dog."
}

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 'https://sift.srv1996466.hstgr.cloud/v1/transcribe?url=https%3A%2F%2Fsift.srv1996466.hstgr.cloud%2Fsamples%2Fspeech.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 - 'https://sift.srv1996466.hstgr.cloud/v1/transcribe?url=https%3A%2F%2Fsift.srv1996466.hstgr.cloud%2Fsamples%2Fspeech.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%2Fsift.srv1996466.hstgr.cloud%2Fv1%2Ftranscribe
const res = await pay("https://sift.srv1996466.hstgr.cloud/v1/transcribe?url=https%3A%2F%2Fsift.srv1996466.hstgr.cloud%2Fsamples%2Fspeech.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.get("https://sift.srv1996466.hstgr.cloud/v1/transcribe?url=https%3A%2F%2Fsift.srv1996466.hstgr.cloud%2Fsamples%2Fspeech.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 agoPassed402134 ms$0.02
7 h agoPassed402160 ms$0.02
11 h agoPassed402145 ms$0.02
16 h agoPassed402308 ms$0.02
20 h agoPassed402215 ms$0.02
Show 10 older checks
24 h agoPassed402315 ms$0.02
28 h agoPassed402247 ms$0.02
32 h agoPassed402195 ms$0.02
36 h agoPassed402298 ms$0.02
40 h agoPassed402176 ms$0.02
44 h agoPassed402150 ms$0.02
2 days agoPassed402130 ms$0.02
2 days agoExpected HTTP 402, got 404404249 ms-
2 days agoPassed402240 ms$0.02
3 days agoPassed402288 ms$0.02