Speech-to-text

Transcribe audio to text using OpenAI (gpt-transcribe). Send POST /api/transcribe with the required field url and pay $0.030 per call over x402 or MPP (there is no free tier). It returns a JSON object with model, provider, text, language and duration.

Provide a URL to an audio file (mp3, wav, m4a, etc.) and get back the transcript. Add diarize:true for speaker labels and word timestamps (ElevenLabs Scribe v2, same price). No API key needed; pay per call via x402. Max 4 minutes of audio, 25 MB file size; /api/transcribe-pro takes the same models to 10 minutes.

Category: AI & compute · Tags: stt speech-to-text transcription audio whisper openai gpt-transcribe · Also found as: speech-to-text stt transcription

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/api/transcribe \
  -H "Content-Type: application/json" \
  -d '{"url":"https://agent402.tools/fixtures/sample-speech.wav"}'

Without payment this returns HTTP 402 Payment Required with the exact price for transcribe; any x402 v2 or MPP client pays it and retries.

Example response

{
  "model": "gpt-transcribe",
  "provider": "openai",
  "text": "Hi, this is the Agent402 sample recording. Can you hear me clearly? Yes, loud and clear. There are two of us on this clip, so the transcript can tell us apart.",
  "language": "en",
  "duration": 12.6
}

From an MCP client

catalog.call {
  "slug": "transcribe",
  "params": {
    "url": "https://agent402.tools/fixtures/sample-speech.wav"
  }
}

The hosted connector at https://agent402.tools/mcp needs a payment for transcribe; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.

Errors and behavior

• url is required. An input the tool rejects returns an HTTP 4xx whose body carries error, tool, expected, required and example, so the caller can correct it.
• A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
• Wallet-only: this tool runs a model, so it has no proof-of-work tier. A prepaid card-credits key issued earlier (Authorization: Bearer a402_...) also pays it.
• Model-backed: the answer is generated by a model, so the same input can produce different wording.
• A GET or HEAD to /api/transcribe returns the same 402 quote, so the price can be read without a body.
• An Idempotency-Key header makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB is not replayed).

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();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/transcribe", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "url": "https://agent402.tools/fixtures/sample-speech.wav"
  }),
});

Part of these workflows

Speech-to-text is one step in this skill pack, each sold as a single call:

• Subtitle pipeline - Audio URL → finished subtitles in one call: transcribe the audio, emit the transcript as SRT/WebVTT/JSON cues, and report the text statistics - length, reading time, word count.

Related tools