x402factory.ai

{
  "input": {
    "bodyFields": {
      "action": {
        "description": "Optional action. Omit for TTS. Use 'list' to list available voices instead of generating speech.",
        "enum": [
          "list"
        ],
        "required": false,
        "type": "string"
      },
      "text": {
        "description": "Text to convert to speech when action is omitted (TTS mode). Required for paid TTS calls.",
        "required": false,
        "type": "string"
      },
      "voice_id": {
        "description": "Optional ElevenLabs voice_id. If omitted, a default narrator voice is used.",
        "required": false,
        "type": "string"
      }
    },
    "bodyType": "json",
    "method": "POST",
    "type": "http"
  },
  "output": {
    "action": {
      "description": "Action performed: 'tts' for text-to-speech, 'list' for voice listing.",
      "type": "string"
    },
    "chars": {
      "description": "Number of characters used for pricing in TTS calls.",
      "type": "number"
    },
    "ok": {
      "description": "True on success",
      "type": "boolean"
    },
    "price_usdc": {
      "description": "Price charged for this call in USDC (6 decimals, rounded up). Minimum is 0.001 USDC.",
      "type": "number"
    },
    "tts_url": {
      "description": "Public URL of the generated audio file hosted on ImageKit (TTS only).",
      "type": "string"
    },
    "voice_id": {
      "description": "Voice ID used for the TTS call (TTS only).",
      "type": "string"
    },
    "voices": {
      "description": "For action=list: available voices with trimmed metadata (voice_id, name, accent, descriptive, age, language, use_case).",
      "type": "array"
    }
  }
}