You need some sort of hardware that HA can connect to and use as a pipeline. The rudimentary one was an Atom M5stack Echo and it had a wakeword process on it that used openwakeword service on HA, and then shipped TTS and STT over the network from Piper and Whisper over Wyoming protocol.

That's a complicated explanation, but essentially you installed an ESPHome config on the Atom and it would find those services and then use it for spk/mic as a voice assistant pipeline. See https://www.home-assistant.io/voice_control/thirteen-usd-voice-remote/#installing-the-software-onto-the-atom-echo

Nabu Casa was putting out a voice satellite hardware, I'm not sure where that's sitting these days, they might have sold out of the production run. But there are a few others being built, you might find something that works for you. I think FutureProofHome youtube channel was coming out with one too.