Text-to-speech — short (≤2k)

• POST

  /paid/compute/tts▾

  Natural speech, instantly - English (6 voices) and Korean. Kokoro + MeloTTS engines; wav or mp3 output; voice and speed control per request; up to 2,000 chars (Korean 1,200). Failed calls are never charged. For longer text, use Text-to-speech — narration.

  HPP Mainnet$0.008

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

  Scheme	Network	Asset	Price
  exact	HPP Mainnet	USDC.e	$0.008

  Request & response

  POSTjson

  Request body

  Field	Type	Required	Description
  text	string	required	Text to speak, up to 2,000 characters (Korean up to 1,200)
  speed	number	optional	0.5 to 2.0, default 1.0
  voice	string	optional	af_heart (default), af_bella, am_adam, am_michael, bf_emma, bm_george, or ko for Korean
  format	string(wav | mp3)	optional	Audio format, default wav

  Example response

  {
    "engine": "kokoro",
    "format": "wav",
    "audio_b64": "<base64 wav>",
    "duration_s": 2.4
  }

  Raw discovery info

  {
    "input": {
      "body": {
        "text": "Hello from the paid compute rail.",
        "voice": "af_heart",
        "format": "mp3"
      },
      "type": "http",
      "method": "POST",
      "bodyType": "json"
    },
    "output": {
      "type": "json",
      "example": {
        "engine": "kokoro",
        "format": "wav",
        "audio_b64": "<base64 wav>",
        "duration_s": 2.4
      }
    }
  }

• MCP

  compute_tts▾

  Natural speech, instantly - English (6 voices) and Korean. Kokoro + MeloTTS engines; wav or mp3 output; voice and speed control per request; up to 2,000 chars (Korean 1,200). Failed calls are never charged. For longer text, use Text-to-speech — narration.

  HPP Mainnet$0.008

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

  Scheme	Network	Asset	Price
  exact	HPP Mainnet	USDC.e	$0.008

  Request & response

  Example response

  {
    "engine": "kokoro",
    "format": "wav",
    "audio_b64": "<base64 wav>",
    "duration_s": 2.4
  }

  Raw discovery info

  {
    "input": {
      "type": "mcp",
      "example": {
        "args": {
          "text": "Hello from the paid compute rail.",
          "voice": "af_heart"
        }
      },
      "toolName": "compute_tts",
      "transport": "streamable-http",
      "description": "Turn text into natural speech and get the audio back as wav or mp3. English (6 voices) and Korean. Up to 2,000 characters per call.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "args": {
            "type": "object",
            "required": [
              "text"
            ],
            "properties": {
              "text": {
                "type": "string",
                "maxLength": 2000,
                "minLength": 1,
                "description": "Text to speak, up to 2,000 characters (Korean up to 1,200)"
              },
              "speed": {
                "type": "number",
                "description": "0.5 to 2.0, default 1.0"
              },
              "voice": {
                "type": "string",
                "description": "af_heart (default), af_bella, am_adam, am_michael, bf_emma, bm_george, or ko for Korean"
              },
              "format": {
                "enum": [
                  "wav",
                  "mp3"
                ],
                "type": "string",
                "description": "Audio format, default wav"
              }
            }
          }
        },
        "additionalProperties": false
      }
    },
    "output": {
      "type": "json",
      "example": {
        "engine": "kokoro",
        "format": "wav",
        "audio_b64": "<base64 wav>",
        "duration_s": 2.4
      }
    }
  }

Recent settlements