I have home assistant voice preview setup with OpenAI. And I have made script that can have openAI generate an image and send it to me via notification.
My next challenge and roadblock is being able to vocally ask voice assistant to generate an image of something and use that as the prompt in the script.
I’m guessing it would be an automation that is exposed that somehow captures my initial voice as a variable that can be passed to the script?
Any direction and help is appreciated.
1 post - 1 participant