TextToSpeechResponse

{
    "endpoint": "POST /v1/text-to-speech",
    "result": {
        "audioFormat": "string",
        "audioData": "string",
        "audioSeconds": 0,
        "ttsCharacters": 0,
        "voice": "string",
        "locale": "string",
        "generatedAt": "2019-08-24T14:15:22.123Z"
    }
}