Best practices for speech recognition?

0 favourites
  • 1 posts
From the Asset Store
Whisper is a speech recognition system for making requests to the OpenAI speech to text API
  • I'm attempting to build my first game using Construct 2. Currently, players will interact with a physical robot hosted in a public space. Initially, he will appear asleep, but touching any of his inputs will wake him up and start the game.

    I'm having trouble understanding some basic variable mechanics to allow me to guide the conversation linearly or otherwise.

    Currently, I'm using a global variable "Step" to indicate where they are in the conversation. I'm using another variable "Keyword" which is triggered when the correct response is given. By default Keyword is set to -1 and each Step sets Keyword to find(PlayerSpeech.text,"triggerword"). Although, I'm having trouble allowing multiple keywords/triggerwords to jump the next interaction, or I'm not understanding how the find function works exactly.

    For example, after pressing a key to wake him up, the player will need to say his name for him to respond. His name, "Berty", is not a common word and can be parsed a variety of ways (e.g. Liberty, pretty, 30, ect.). I need to have a way for each instance which is close to it to nudge the Keyword variable out of it's false state. I can effectively do this when only one Keyword is listed, but nothing is happening when I attempt to list multiple.

    How can I do this? Or is there a better way entirely?

    Here's a link to my project file.

  • Try Construct 3

    Develop games in your browser. Powerful, performant & highly capable.

    Try Now Construct 3 users don't see these ads
Jump to:
Active Users
There are 1 visitors browsing this topic (0 users and 1 guests)