80trust / 100

Audio Transcribe

by Tanod mlpeek in AI models & inference

x402 APIPassing, checked 3 min ago

mlpeek (Tanod) speech to text and subtitles: an audio file of up to 10 minutes as text, timed segments, SRT and WebVTT (faster-whisper). Use when an agent must turn a spoken-audio file of up to 10 minutes into text, timed segments or SRT captions.

POST https://tanod.dev/v1/audio/transcribe

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
272 ms typical, 279 ms slowest 5%
Last check
3 min ago
Next check
in 26 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://tanod.dev/v1/audio/transcribe" \
  -H "content-type: application/json" \
  -d '{"url":"https://tanod.dev/samples/speech-sample.mp3"}'
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%2Ftanod.dev%2Fv1%2Faudio%2Ftranscribe
const res = await pay("https://tanod.dev/v1/audio/transcribe", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"url":"https://tanod.dev/samples/speech-sample.mp3"}),
});
console.log(await res.json());

Example input

{
  "url": "https://tanod.dev/samples/speech-sample.mp3"
}

Example output

{
  "duration": 11,
  "input_bytes": 1152693,
  "language": "en",
  "language_probability": 0.9528,
  "model": {
    "compute": "int8",
    "id": "faster-whisper-base",
    "revision": "ebe41f70d5b6dfa9166e2c581c45c9c0cfc57b66",
    "source": "Systran/faster-whisper-base"
  },
  "operation": "audio-transcribe",
  "segments": [
    {
      "end": 11,
      "start": 0,
      "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country."
    }
  ],
  "srt": "1\n00:00:00,000 --> 00:00:11,000\nAnd so my fellow Americans ask not what your country can do for you, ask what you can do for your country.\n\n",
  "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.",
  "truncated": false,
  "untrusted_content": true,
  "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:11.000\nAnd so my fellow Americans ask not what your country can do for you, ask what you can do for your country.\n\n"
}

Security scan

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

Recent checks

WhenResultHTTPTimePrice
3 min agoPassed402269 ms$0.01
4 h agoPassed402276 ms$0.01
7 h agoPassed402276 ms$0.01
11 h agoPassed402272 ms$0.01
15 h agoPassed402279 ms$0.01
18 h agoPassed402286 ms$0.01
22 h agoPassed402261 ms$0.01
26 h agoPassed402267 ms$0.01
29 h agoPassed402264 ms$0.01
34 h agoPassed402272 ms$0.01