AgentUtility.ai

Transcribe video or audio URLs into timestamped text with Whisper v3 large. Send media_url with an optional language hint and task, then receive full text, timestamped chunks, detected languages, duration, task, and source URL. Choose translate to return English text. Handles files up to 60 minutes or 500MB. Use it as a transcribe API, video transcription API, audio transcription service, or video

Open endpoint ↗

Price per call: $0.10
Chain: Base
Method: POST
Paid calls · 30 days: 2

Call it from code

This API is run by its own provider and paid directly through x402. We list it so you can find it; we don't route or hold the payment.

import { x402Client, wrapFetchWithPayment } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";

const client = new x402Client();
registerExactEvmScheme(client, { signer: agentAccount });

const pay = wrapFetchWithPayment(fetch, client);
const res = await pay("https://x402.agentutility.ai/video-transcribe", { method: "POST" });
console.log(await res.json());

https://x402.agentutility.ai/video-transcribe