Alexa: Can we access the actual voice input by the user inside the lambda function?

Question

Is it possible to access the text (converted from voice) spoken by the user? Is there a switch somewhere, which if enabled, the text is sent to the skill?

Answer 1

No, we won't get the entire user input.

However, we can capture parts of user speech by using slots. There are different slots types and the one which you should look into is AMAZON.SearchQuery.

AMAZON.SearchQuery slot type lets you capture less-predictable input that makes up the search query.

{
  "intents": [
    {
      "name": "SearchIntent",
      "slots": [
        {
          "name": "Query",
          "type": "AMAZON.SearchQuery"
        },
        {
          "name": "CityList",
          "type": "AMAZON.US_CITY"
        }
      ],
      "samples": [
        "search for {Query} near me",
        "find out {Query}",
        "search for {Query}",
        "give me details about {CityList}"
      ]
    }
  ]
}

More on AMAZON.SearchQuery here

There is AMAZON.LITERAL slot that passes the recognized words for the slot value with no conversion. But, its's not recommended. You cannot use AMAZON.LITERAL in a skill configured with a dialog model