Agent402 / tools / audio-convert

Audio convert (to MP3)

$0.02 per call · USDC via x402 · POST /api/audio-convert

Extract/convert the audio track of any media URL (mp4, mov, wav, m4a, ogg…) to MP3 — the "mp4 to mp3" conversion, deterministic ffmpeg, no AI. Body: {"url":"https://…/video.mp4","bitrate":"192k"?}. Returns the MP3 as base64.

Input

FieldTypeDescription
url *stringPublic URL of the media file (max 30MB)
bitratestringMP3 bitrate, e.g. "128k", "192k" (default), "320k"

Example output

{
  "format": "mp3",
  "bitrate": "192k",
  "bytes": 2210000,
  "mp3Base64": "SUQzBAAAAA…"
}

Try it — see the 402 challenge (free)

curl -i -X POST https://agent402.tools/api/audio-convert \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/talk.mp4"}'

The response is HTTP 402 Payment Required with exact payment requirements. Any x402 v2 client pays automatically and retries:

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/audio-convert", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "url": "https://example.com/talk.mp4"
  }),
});

Wallet-only. This tool reaches the network/browser/storage, so it is paid in USDC via x402 (no proof-of-work tier).

Related tools

Extract article

USDC $0.005 · POST /api/extract

Extract the main article content from any public URL as clean markdown. Returns title, byline, excerpt, word count, and …

Page metadata

USDC $0.002 · GET /api/meta

Fetch page metadata for a URL: title, description, OpenGraph, Twitter cards, canonical URL, favicon.

Browser render

USDC $0.02 · POST /api/render

Render a page in a real headless Chromium browser (JavaScript executed), then extract the main content as clean markdown…