78trust / 100

Routes Transcribe Long

by Dicta-Notes in AI models & inference

x402 APIPassing, checked 1 h ago

Turn a full recording into a structured document: POST JSON with an audio_url — up to 2 HOURS of meeting, interview, hearing, or podcast audio — and get a diarized who-said-what transcript JSON: timestamps, speaker tracking with per-segment confidence, language codes. Most transcription APIs cap at ~20 minutes; this one runs Gemini long-context, built for the long ones. mp3, wav, m4a, ogg, webm, flac. Flat price, USDC on Base, no account.

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

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
210 ms typical, 277 ms slowest 5%
Last check
1 h 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-long" \
  -H "content-type: application/json" \
  -d '{"audio_url":"https://example.com/meeting.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-long
const res = await pay("https://dicta-notes.com/routes/x402/transcribe-long", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"audio_url":"https://example.com/meeting.mp3","store":false}),
});
console.log(await res.json());

Example input

{
  "audio_url": "https://example.com/meeting.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
1 h agoPassed402277 ms$0.59
5 h agoPassed402220 ms$0.59
8 h agoPassed402210 ms$0.59
12 h agoPassed402203 ms$0.59
15 h agoPassed402297 ms$0.59
19 h agoPassed402215 ms$0.59
23 h agoPassed402216 ms$0.59
26 h agoPassed402208 ms$0.59
30 h agoPassed402197 ms$0.59
34 h agoPassed402179 ms$0.59
37 h agoPassed402196 ms$0.59
42 h agoPassed402223 ms$0.59