This isn’t merely a speech-to-text thing. It also provides intent recognition, which makes it great for doing voice commands. For example, when trained with this template, the following command:

$ voice2json transcribe-wav \
      < turn-on-the-light.wav | \
      voice2json recognize-intent | \
      jq .

Produces this JSON event:

{
    "text": "turn on the light",
    "intent": {
        "name": "LightState"
    },
    "slots": {
        "state": "on"
    }
}

And it can be retrained quickly enough to do it at runtime. Cool stuff!