{
  "x402Version": 2,
  "id": 4068,
  "slug": "4068",
  "resource": "https://api.delx.ai/api/v1/x402/speech-hd",
  "description": "Generate high-fidelity expressive speech for $0.08 USDC. Call when you need English, Portuguese, or Spanish voiceover with emotion, speed, and pitch for up to 500 UTF-8 bytes—not a phone carrier or realtime session. Returns a validated 32 kHz mono WAV URL and SHA-256 receipt. No API key, no subscription.",
  "type": "http",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0x9f8bd9875b3E0b632a24A3A7C73f7787175e73A2",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "80000",
      "maxTimeoutSeconds": 300
    },
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0x9f8bd9875b3E0b632a24A3A7C73f7787175e73A2",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "80000",
      "maxTimeoutSeconds": 300
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "28heAMpFkeUJsL7o7apiK4oJwZWq2fUHinRwbgYYsemG",
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "amount": "80000",
      "maxTimeoutSeconds": 300
    }
  ],
  "outputSchema": {
    "bazaar": {
      "category": "audio",
      "info": {
        "input": {
          "body": {
            "emotion": "happy",
            "language": "English",
            "pitch": 0,
            "speed": 1,
            "text": "Your autonomous agent completed the mission successfully.",
            "voice": "English_CaptivatingStoryteller"
          },
          "bodyType": "json",
          "method": "POST",
          "type": "http"
        },
        "output": {
          "example": {
            "audio_url": "https://api.delx.ai/api/v1/generated-audio-hd/7de36cd5f5f34ef8a28904b9b5985f60.wav",
            "bytes": 588252,
            "channels": 1,
            "duration_ms": 9172,
            "emotion": "happy",
            "generation_id": "7de36cd5f5f34ef8a28904b9b5985f60",
            "gross_margin_usd": 0.067,
            "input_tokens": 130,
            "language": "English",
            "media_type": "audio/wav",
            "model": "minimax/speech-02-hd",
            "pitch": 0,
            "provider": "replicate",
            "provider_attempts": 1,
            "sale_price_usdc": 0.08,
            "sample_rate_hz": 32000,
            "sample_width_bits": 16,
            "sha256": "7ded32df89c15e721f6e997931b3ee28d40a89635fe35d91b5a496712e95bead",
            "speed": 1,
            "upstream_cost_usd": 0.013,
            "voice": "English_CaptivatingStoryteller"
          },
          "type": "json"
        }
      },
      "schema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "input": {
            "additionalProperties": false,
            "properties": {
              "body": {
                "additionalProperties": false,
                "anyOf": [
                  {
                    "required": [
                      "text"
                    ]
                  },
                  {
                    "required": [
                      "input"
                    ]
                  }
                ],
                "properties": {
                  "emotion": {
                    "default": "auto",
                    "enum": [
                      "auto",
                      "happy",
                      "sad",
                      "angry",
                      "fearful",
                      "disgusted",
                      "surprised",
                      "neutral"
                    ],
                    "type": "string"
                  },
                  "input": {
                    "description": "Alias for text; the UTF-8 encoding must not exceed 500 bytes.",
                    "maxLength": 500,
                    "minLength": 1,
                    "type": "string",
                    "x-maxUtf8Bytes": 500
                  },
                  "language": {
                    "default": "Automatic",
                    "enum": [
                      "Automatic",
                      "English",
                      "French",
                      "German",
                      "Italian",
                      "Japanese",
                      "Korean",
                      "Portuguese",
                      "Spanish"
                    ],
                    "type": "string"
                  },
                  "pitch": {
                    "default": 0,
                    "maximum": 12,
                    "minimum": -12,
                    "type": "integer"
                  },
                  "speed": {
                    "default": 1,
                    "maximum": 2,
                    "minimum": 0.5,
                    "type": "number"
                  },
                  "text": {
                    "description": "Text to synthesize; the UTF-8 encoding must not exceed 500 bytes.",
                    "maxLength": 500,
                    "minLength": 1,
                    "type": "string",
                    "x-maxUtf8Bytes": 500
                  },
                  "voice": {
                    "default": "English_Wiselady",
                    "enum": [
                      "English_Wiselady",
                      "English_Deep-VoicedGentleman",
                      "English_CaptivatingStoryteller",
                      "Portuguese_Wiselady",
                      "Portuguese_Deep-VoicedGentleman",
                      "Portuguese_CaptivatingStoryteller",
                      "Portuguese_Narrator",
                      "Spanish_Wiselady",
                      "Spanish_Deep-tonedMan",
                      "Spanish_CaptivatingStoryteller",
                      "Spanish_Narrator"
                    ],
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "bodyType": {
                "enum": [
                  "json",
                  "form-data",
                  "text"
                ],
                "type": "string"
              },
              "method": {
                "enum": [
                  "POST",
                  "PUT",
                  "PATCH"
                ],
                "type": "string"
              },
              "type": {
                "const": "http",
                "type": "string"
              }
            },
            "required": [
              "type",
              "bodyType",
              "body"
            ],
            "type": "object"
          },
          "output": {
            "properties": {
              "example": {
                "audio_url": "https://api.delx.ai/api/v1/generated-audio-hd/7de36cd5f5f34ef8a28904b9b5985f60.wav",
                "bytes": 588252,
                "channels": 1,
                "duration_ms": 9172,
                "emotion": "happy",
                "generation_id": "7de36cd5f5f34ef8a28904b9b5985f60",
                "gross_margin_usd": 0.067,
                "input_tokens": 130,
                "language": "English",
                "media_type": "audio/wav",
                "model": "minimax/speech-02-hd",
                "pitch": 0,
                "provider": "replicate",
                "provider_attempts": 1,
                "sale_price_usdc": 0.08,
                "sample_rate_hz": 32000,
                "sample_width_bits": 16,
                "sha256": "7ded32df89c15e721f6e997931b3ee28d40a89635fe35d91b5a496712e95bead",
                "speed": 1,
                "upstream_cost_usd": 0.013,
                "voice": "English_CaptivatingStoryteller"
              },
              "type": {
                "const": "json",
                "type": "string"
              }
            },
            "required": [
              "type",
              "example"
            ],
            "type": "object"
          }
        },
        "required": [
          "input",
          "output"
        ],
        "type": "object"
      },
      "serviceName": "MiniMax Speech HD for Agents",
      "summary": "Generate high-fidelity expressive speech for $0.08 USDC. Call when you need English, Portuguese, or Spanish voiceover with emotion, speed, and pitch for up to 500 UTF-8 bytes—not a phone carrier or realtime session. Returns a validated 32 kHz mono WAV URL and SHA-256 receipt. No API key, no subscription.",
      "tags": [
        "x402",
        "text-to-speech",
        "tts",
        "speech-hd",
        "high-fidelity"
      ]
    }
  },
  "tags": [
    "bazaar"
  ],
  "sourceHost": "api.delx.ai",
  "lastUpdated": "2026-08-29T06:45:35.438Z",
  "quality": {
    "calls30d": 1,
    "uniquePayers30d": 1,
    "lastCalledAt": "2026-08-29T06:45:34.773Z"
  },
  "liveness": {},
  "verified": false,
  "featured": false,
  "provider": {
    "host": "api.delx.ai",
    "manifest_name": "api.delx.ai",
    "source": "cdp-mirror",
    "source_manifest_url": "https://api.cdp.coinbase.com/platform/v2/x402/discovery/resources",
    "submitted_at": "2026-09-18T22:00:31.484Z"
  }
}