I am working on a skill to interface with OpenAI’s davinci-003 or ChatGPT. I have everything working in a basic python program, but haven’t started the skill yet. The biggest issue is that I want to be able to create a variable that would capture what I say as a string. Right now, I have to create my own prompts or predefine everything by physically typing it in, but this hinders the ability to utilize ChatGPT. I would like to capture my speech instead. Would this come from the cli or message bus? Any help would be awesome. Thank you!
The skill class defines a ‘get_response’ method, which can speak some dialogue, and then wait for the user’s spoken response: mycroft-core/mycroft_skill.py at dev · MycroftAI/mycroft-core · GitHub
If you’d like to see example usage, it’s used quite a bit in the routine skill: mycroft_routine_skill/__init__.py at master · ChristopherRogers1991/mycroft_routine_skill · GitHub