78trust / 100

Routes Transcribe

by Dicta-Notes in AI models & inference

x402 APIPassing, checked 53 min ago

Transcribe short audio fast: POST JSON with an audio_url (voicemail, call recording, voice memo, podcast clip — up to 15 min) and get Gemini-powered transcript JSON back with speaker-labeled, timestamped segments — any spoken language, auto-detected and labeled per segment. Handles mp3, wav, m4a, ogg, webm, flac. $0.10 flat in USDC on Base — no account, no API key. For hour-long meetings use /routes/x402/transcribe-long.

POST https://dicta-notes.com/routes/x402/transcribe

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
193 ms typical, 243 ms slowest 5%
Last check
53 min ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://dicta-notes.com/routes/x402/transcribe" \
  -H "content-type: application/json" \
  -d '{"audio_url":"https://example.com/voicemail.mp3","store":false}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fdicta-notes.com%2Froutes%2Fx402%2Ftranscribe
const res = await pay("https://dicta-notes.com/routes/x402/transcribe", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"audio_url":"https://example.com/voicemail.mp3","store":false}),
});
console.log(await res.json());

Example input

{
  "audio_url": "https://example.com/voicemail.mp3",
  "store": false
}

Example output

{
  "duration_seconds": 512.3,
  "language": "en",
  "languages_detected": [
    "en"
  ],
  "segments": [
    {
      "confidence": 0.85,
      "end_time": 5.2,
      "language": "en",
      "speaker": "Speaker 1",
      "start_time": 0,
      "text": "What they said"
    }
  ],
  "speakers": [
    "Speaker 1",
    "Speaker 2"
  ],
  "transcript": "Full plain-text transcript, segments joined in order…"
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
53 min agoPassed402243 ms$0.1
5 h agoPassed402170 ms$0.1
8 h agoPassed402141 ms$0.1
12 h agoPassed402144 ms$0.1
15 h agoPassed402197 ms$0.1
19 h agoPassed402255 ms$0.1
23 h agoPassed402193 ms$0.1
26 h agoPassed402212 ms$0.1
30 h agoPassed402153 ms$0.1
34 h agoPassed402161 ms$0.1
37 h agoPassed402221 ms$0.1
42 h agoPassed402219 ms$0.1