{
  "version": 1,
  "x402Version": 2,
  "resources": [
    "https://voice.madebydevx.com/v1/stt",
    "https://voice.madebydevx.com/v1/tts",
    "https://voice.madebydevx.com/v1/translate",
    "https://voice.madebydevx.com/v1/ocr"
  ],
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "amount": "2000",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "payTo": "0xe30c4544eC57ac44d8586eB49e49e267fc2d40DB",
      "maxTimeoutSeconds": 300,
      "extra": {
        "name": "USD Coin",
        "version": "2"
      }
    }
  ],
  "endpoints": [
    {
      "url": "https://voice.madebydevx.com/v1/stt",
      "resource": "https://voice.madebydevx.com/v1/stt",
      "type": "http",
      "method": "POST",
      "description": "Speech to text for agents: send an audio URL, base64 or raw audio (WAV, MP3, FLAC, OGG, M4A, WebM; up to 20 min / 10 MB) and get the transcript, language, timed segments and WebVTT subtitles. Optional task=translate gives English text. $0.002 USDC per started minute on Base; failed or silent audio is not charged. Whisper large-v3-turbo. By DevX.",
      "mimeType": "application/json",
      "serviceName": "DevX Voice",
      "tags": [
        "speech-to-text",
        "stt",
        "transcription",
        "whisper",
        "audio"
      ],
      "x402Version": 2,
      "accepts": [
        {
          "scheme": "exact",
          "network": "eip155:8453",
          "amount": "2000",
          "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
          "payTo": "0xe30c4544eC57ac44d8586eB49e49e267fc2d40DB",
          "maxTimeoutSeconds": 300,
          "extra": {
            "name": "USD Coin",
            "version": "2"
          }
        }
      ]
    },
    {
      "url": "https://voice.madebydevx.com/v1/tts",
      "resource": "https://voice.madebydevx.com/v1/tts",
      "type": "http",
      "method": "POST",
      "description": "Text to speech for agents: send text (up to 2,000 chars) in English, Spanish, French, Chinese, Japanese or Korean and get a WAV voice clip (base64 in JSON, or raw audio/wav with response_format=wav). $0.001 USDC per started 1,000 characters on Base; failures are not charged. Accepts dTelecom-style text/lang_code fields. MeloTTS. By DevX.",
      "mimeType": "application/json",
      "serviceName": "DevX Voice",
      "tags": [
        "text-to-speech",
        "tts",
        "speech",
        "voice",
        "audio"
      ],
      "x402Version": 2,
      "accepts": [
        {
          "scheme": "exact",
          "network": "eip155:8453",
          "amount": "1000",
          "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
          "payTo": "0xe30c4544eC57ac44d8586eB49e49e267fc2d40DB",
          "maxTimeoutSeconds": 300,
          "extra": {
            "name": "USD Coin",
            "version": "2"
          }
        }
      ]
    },
    {
      "url": "https://voice.madebydevx.com/v1/translate",
      "resource": "https://voice.madebydevx.com/v1/translate",
      "type": "http",
      "method": "POST",
      "description": "Machine translation for agents between 100 languages: send text (up to 5,000 chars), target_lang and optional source_lang (auto-detect by default) and get the translation. $0.001 USDC per started 1,000 characters on Base; failures are not charged. LibreTranslate/dTelecom-style {q, source, target} also accepted at /v1/translation. M2M100 1.2B. By DevX.",
      "mimeType": "application/json",
      "serviceName": "DevX Voice",
      "tags": [
        "translation",
        "translate",
        "languages",
        "multilingual",
        "m2m100"
      ],
      "x402Version": 2,
      "accepts": [
        {
          "scheme": "exact",
          "network": "eip155:8453",
          "amount": "1000",
          "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
          "payTo": "0xe30c4544eC57ac44d8586eB49e49e267fc2d40DB",
          "maxTimeoutSeconds": 300,
          "extra": {
            "name": "USD Coin",
            "version": "2"
          }
        }
      ]
    },
    {
      "url": "https://voice.madebydevx.com/v1/ocr",
      "resource": "https://voice.madebydevx.com/v1/ocr",
      "type": "http",
      "method": "POST",
      "description": "OCR for agents: send an image URL or base64 (PNG, JPEG, WebP, GIF; up to 3 MB) and get the text it contains in reading order, as plain text or Markdown (tables, lists). Works on screenshots, receipts, invoices, signs and documents. $0.002 USDC per image on Base; images with no readable text are not charged. Gemma 4 vision. By DevX.",
      "mimeType": "application/json",
      "serviceName": "DevX Voice",
      "tags": [
        "ocr",
        "image-to-text",
        "text-extraction",
        "vision",
        "documents"
      ],
      "x402Version": 2,
      "accepts": [
        {
          "scheme": "exact",
          "network": "eip155:8453",
          "amount": "2000",
          "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
          "payTo": "0xe30c4544eC57ac44d8586eB49e49e267fc2d40DB",
          "maxTimeoutSeconds": 300,
          "extra": {
            "name": "USD Coin",
            "version": "2"
          }
        }
      ]
    }
  ],
  "description": "DevX Voice: speech-to-text, text-to-speech, translation and OCR for agents; x402, USDC on Base. Made by DevX.",
  "openapi": "https://voice.madebydevx.com/openapi.json",
  "llms": "https://voice.madebydevx.com/llms.txt"
}