Transcribe audio files to text using Whisper AI. Supports mp3, wav, m4a, ogg, flac. Auto-detects language. Returns full text, timestamps, and per-segment breakdown. 100% local inference on Mac Mini. $0.05 USDC per call.
POST https://x402.ntriq.co.kr/audio-intel
Content-Type: application/json
X-PAYMENT: <x402-payment-header>
{
"audio_url": "https://example.com/speech.mp3"
}
| Parameter | Type | Required | Description |
|---|---|---|---|
| ----------- | ------ | ---------- | ------------- |
audio_url | string | ✅ (or base64) | URL of audio file (mp3/wav/m4a/ogg/flac) |
audio_base64 | string | ✅ (or url) | Base64-encoded audio |
language | string | ❌ | Force language (e.g. en, ko, ja). Default: auto-detect |
{
"status": "ok",
"text": "Hello, this is a test recording for transcription.",
"language": "en",
"language_probability": 0.998,
"duration": 4.32,
"segments": [
{"start": 0.0, "end": 4.32, "text": "Hello, this is a test recording for transcription."}
]
}
curl https://x402.ntriq.co.kr/services
共 1 个版本