In Home Assistant a voice assistant is a combination of a speech-to-text, conversation and text-to-speech engines. A user can create as many combinations as they want. For a conversation agent, it's text command in, text response out. We already have the option to use OpenAI GPT 3.5, so it's possible in the future to hook it up to a large language model and allow it to control your house.
Fun fact: we supported Almond (later Genie), the IoT AI from Stanford which they released a couple of years ago. It would convert natural language into their ThingTalk language, which could do things like you mention. It was not popular at all and Stanford ended up shutting it down.
I remember the Almond days. Back then they were up against Vera which, IMO, was the clear leader. Then the guys from SmartThings happened to come out with their product which I saw at a MinneStar event. I asked one of the founders after the preso what their perspective on cloud connected services was and the guy couldn't believe I had an opinion on a home automation system that couldn't operate without cloud services. They're were clearly going after a much simpler consumer market and looking to sell out, of which they did. But it was a disaster for anyone that was used to the configurability and flexibility of Vera. Then Vera started to lose focus and HomeSeer seemed to come up as a viable replacement, along with the early days of HomeAssistant. It's interesting that HA is only getting better while all the rest are slowly dying off. HomeSeer v4 is still pretty rough transition from v3. I only hope HA stays the course and continues to hold their high standards. It's such a phenomenal project. From simple to complex automation, it is truly a great work of open source.
Fun fact: we supported Almond (later Genie), the IoT AI from Stanford which they released a couple of years ago. It would convert natural language into their ThingTalk language, which could do things like you mention. It was not popular at all and Stanford ended up shutting it down.