I for one am greatly looking forward to the day these kind of voice models can be run locally. It seems like the gap between open-weight and frontier is way larger for voice models than coding/language models.
Probably not _as_ good, but you can run gemma 4 for the ears/brain (accepts audio input), and kokoro TTS for the mouth. You want something like silero VAD sitting in front of the LLM so you aren't passing wasteful audio to gemma 4, so you send only voice activity segments. I type all this because I tried it out recently as a Zork experience, seeing how creative Gemma 4 12B could be. It was surprisingly good!
Yeah, I mostly mean for the TTS, which in my testing is flat and has no emotional register, or no nuanced variation. OpenAI speech in my experience is very good at things like communicating understanding or questions non-verbally using intonation, and I'm yet to see a local TTS model that will do contextual intonation well at all.