$0.025
per call · USD Coin on Base
Transcribe up to five minutes of base64 audio in the isolated local media worker. Returns detected language, duration, and text without retaining the source audio or transcript.
Endpoint
POST https://fetchharbor.benlab.download/audio/transcribe1
Calls / 30d
1
Unique payers / 30d
Aug 23
Last called
exact
Payment scheme
Call this service
import { wrapFetchWithPayment } from "@x402/fetch";
import { privateKeyToAccount } from "viem/accounts";
const account = privateKeyToAccount(process.env.PRIVATE_KEY);
const fetchWithPay = wrapFetchWithPayment(fetch, account);
const res = await fetchWithPay("https://fetchharbor.benlab.download/audio/transcribe", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
"audio_base64": "UklGRg..."
}),
});
const data = await res.json();curl -X POST \
"https://fetchharbor.benlab.download/audio/transcribe" \
-H "Content-Type: application/json" \
-d '{"audio_base64":"UklGRg..."}' \
-H "X-PAYMENT: <signed x402 payment>"Example response
{
"duration_seconds": 1.2,
"language": "en",
"model": "faster-whisper-small",
"status": "success",
"text": "Hello"
}Payment details
0xaed4a496fed1132b94c0a5f9fb5ee7cf63d869c2USD Coin · 0x833589fcd6edb6e08f4c7c32d4f71b54bda02913Is this your API?
Pin it to the top of Media & Generation and the homepage with a featured placement.
More from Benlab & similar services
Benlab · Scrape
fetchharbor.benlab.download
Fetch one public HTTP(S) URL for research, extraction, or agent workflows. Returns the final URL, upstream status, content type, and decoded content. Private, local, metadata, and reserved destinations are blocked; redirects are revalidated and response size and duration are bounded.
Benlab · Html TO MD
fetchharbor.benlab.download
Convert a supplied HTML string into deterministic, LLM-ready Markdown. Preserves headings, links, lists, emphasis, and code without fetching a URL or invoking an AI model. Input is bounded to 2,000,000 characters.
Benlab · Chat
fetchharbor.benlab.download
Generate one bounded assistant response with the operator's self-hosted Ollama model. Use for short, single-message inference where local processing is preferred. Accepts up to 8,000 characters and returns the model name, response text, and token counts when Ollama supplies them.