Speech-to-text — clips (≤3 min)

• POST

  /paid/compute/stt▾

  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.

  HPP Mainnet$0.01

  https://agent.hpp.io/paid/compute/stt

  Scheme	Network	Asset	Price
  exact	HPP Mainnet	USDC.e	$0.01

  Request & response

  POSTjson

  Request body

  Field	Type	Required	Description
  language	string	optional	ISO code like ko or en; default auto-detect
  audio_b64	string	optional	Base64-encoded audio - provide exactly one of audio_b64 or audio_url
  audio_url	string	optional	Public http(s) URL of an audio file (server-side fetch) - provide exactly one of audio_b64 or audio_url
  timestamps	boolean	optional	Include per-segment start/end times

  Example response

  {
    "text": "hello world",
    "language": "en",
    "duration_s": 3.2
  }

  Raw discovery info

  {
    "input": {
      "body": {
        "language": "auto",
        "audio_url": "https://example.com/clip.mp3"
      },
      "type": "http",
      "method": "POST",
      "bodyType": "json"
    },
    "output": {
      "type": "json",
      "example": {
        "text": "hello world",
        "language": "en",
        "duration_s": 3.2
      }
    }
  }

• MCP

  compute_stt▾

  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.

  HPP Mainnet$0.01

  https://agent.hpp.io/mcp/tools/compute_stt

  Scheme	Network	Asset	Price
  exact	HPP Mainnet	USDC.e	$0.01

  Request & response

  Example response

  {
    "text": "hello world",
    "language": "en",
    "duration_s": 3.2
  }

  Raw discovery info

  {
    "input": {
      "type": "mcp",
      "example": {
        "args": {
          "language": "auto",
          "audio_b64": "<base64 of a wav/mp3 clip>"
        }
      },
      "toolName": "compute_stt",
      "transport": "streamable-http",
      "description": "Turn speech into text. Send up to 3 minutes of audio and get the transcript back - Korean, English and 97 other languages, auto-detected. Powered by Whisper.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "args": {
            "type": "object",
            "required": [
              "audio_b64"
            ],
            "properties": {
              "language": {
                "type": "string",
                "description": "ISO code like ko or en; default auto-detect"
              },
              "audio_b64": {
                "type": "string",
                "minLength": 8,
                "description": "Base64-encoded audio (wav/mp3/m4a/ogg/webm), up to 3 minutes / 8MB decoded"
              },
              "timestamps": {
                "type": "boolean",
                "description": "Include per-segment start/end times"
              }
            }
          }
        },
        "additionalProperties": false
      }
    },
    "output": {
      "type": "json",
      "example": {
        "text": "hello world",
        "language": "en",
        "duration_s": 3.2
      }
    }
  }

Recent settlements