无法从Google API获得语音识别结果？

Question

我开始向我们https://cloud.google.com/speech/ 测试演示对我有用，但是当我尝试使用自己的文件时 它似乎不起作用。

我尝试了https://speech.googleapis.com/v1beta1/speech:syncrecognize

{
      "config": {
          "encoding":"LINEAR16",
          "sample_rate": 16000
        },
      "audio": {
        "uri":"gs://test-speech-recognition/arth_the_rat.mp3"
      }
}

获取{}

还试过异步获取

{
  "name": "7572699807343070889",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.speech.v1beta1.AsyncRecognizeMetadata",
    "progressPercent": 100,
    "startTime": "2016-09-10T21:15:59.019595Z",
    "lastUpdateTime": "2016-09-10T21:16:07.687943Z"
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.speech.v1beta1.AsyncRecognizeResponse"
  }
}

我做错了什么？