Short audio transcription (Whisper)
transcribe_short_audioRead-onlyIdempotent
Transcribe one short audio file (direct public URL to MP3, WAV, M4A, OGG, FLAC or WebM; one file up to 2 MB and 20 minutes) with Whisper large-v3-turbo, or translate it to English: text, timed segments, WebVTT and detected language. No YouTube or social media pages. Paid only: $0.01 USDC per file. Paid calls made without a payment return isError with the x402 v2 PaymentRequired object (amount in USDC atomic units, network, payTo, HTTP endpoint); retry with the signed PaymentPayload in params._meta["x402/payment"]. Invalid input and calls where every item fails are never charged. Fetches follow robots.txt, use the User-Agent AdamHaleTools/1.0 and refuse private or internal addresses.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Direct public URL of the audio file. | |
| task | No | translate = English output. | transcribe |
| language | No | Optional spoken language, ISO 639-1 (en, de, es…). | |
| vad_filter | No | false turns off silence filtering. | |
| x402_payment | No | Optional, paid tier only: a signed x402 v2 PaymentPayload, base64 (the value an HTTP client sends as the PAYMENT-SIGNATURE header). Prefer params._meta["x402/payment"]. Never a private key or seed phrase. |