Speech-to-text — clips (≤3 min)

{
  "name": "Speech-to-text — clips (≤3 min)",
  "tags": [
    "stt",
    "speech",
    "transcription",
    "whisper",
    "audio"
  ],
  "type": "https://eips.ethereum.org/EIPS/eip-8004",
  "services": [
    {
      "name": "https://agent.hpp.io/paid/compute/stt",
      "method": "POST",
      "endpoint": "https://agent.hpp.io/paid/compute/stt",
      "transport": "http",
      "description": "Accurate transcription in seconds - 99 languages, auto-detected. Powered by Whisper. Send audio as base64 or just pass a public audio_url (wav/mp3/m4a/ogg/webm, up to 3 minutes); returns the transcript with language confidence and optional timestamps. Failed calls are never charged. For audio over 3 minutes, use Speech-to-text — long-form.",
      "paymentRequired": true
    },
    {
      "name": "compute_stt",
      "endpoint": "https://agent.hpp.io/mcp/tools/compute_stt",
      "toolName": "compute_stt",
      "transport": "mcp",
      "description": "Accurate transcription in seconds - 99 languages, auto-detected. Powered by Whisper. Send audio as base64 or just pass a public audio_url (wav/mp3/m4a/ogg/webm, up to 3 minutes); returns the transcript with language confidence and optional timestamps. Failed calls are never charged. For audio over 3 minutes, use Speech-to-text — long-form.",
      "paymentRequired": true
    }
  ],
  "description": "Accurate transcription in seconds - 99 languages, auto-detected. Powered by Whisper. Send audio as base64 or just pass a public audio_url (wav/mp3/m4a/ogg/webm, up to 3 minutes); returns the transcript with language confidence and optional timestamps. Failed calls are never charged. For audio over 3 minutes, use Speech-to-text — long-form.",
  "x402Support": true,
  "supportedTrust": [
    "feedback"
  ]
}