2
PineVoice Smart Speaker - PINE STORE
pine64.comFeatures: Supports local wake word detection Dual microphone array Provides audio volume control and hardware microphone mute buttons Default firmware supports Wyoming Satellite protocol For more info, please visit PineVoice wiki page: https://wiki.pine64.org/wiki/PineVoice About: CPU: Bouffalo BL606P (1x T-Head C906@480 MHz, 1x T-Head E907@320MHz) Memory: 32 MiB pSRAM, 788KB SRAM Storage: 16 MiB Flash Wireless: Wi-Fi 802.11 b/g/n, Bluetooth 5.x Dual-mode (BT+BLE) Package: Includes USB-A to USB-C power cable Dimension: 65mm x 65 mm x 66mm PLEASE NOTE The PineVoice still in early stage development cycle and may suffer on some performance issues such as wake word detection. Please refer to wiki page for regular firmware update Warranty: 30 days



Very cool!
The voice sattelites like this and the Home Assistant voice from a year back are great and I love seeing more options for self hosted fully local devices like this.
But honestly, what I find is missing for a fully local smart home setup is a “brain” for running the assistant LLM in a simple way.
There is plenty of cloud solutions for connecting AI, but true local hosting requires a rig with a proper GPU if you want timely responses. I wonder if it is possible to build a purpose built “brain box” for Home Assistant that is small, not too expensive, fully local.
It just sucks needing a rig with a RTX 3090 or whatever to get the full chain to run fully local. Small LLMs are stupid as dirt and our Home Assistant Green is in no way equipped to handle any form of LLM. I managed to get my gaming rig to host an LLM that was good enough, but I don’t want my gaming rig to be always on, and if I start gaming on it, the GPU has to deallocate all LLM business.
I love fully local stuff, but the LLM part seems very expensive. Even for such a simple thing as managing our lights and music.
I’m just gonna shamelessly plug my project here: https://github.com/charludo/hass-closest-intent
You do need local STT, but it’s fine if it’s somewhat bad; the conversation agent linked is sufficient to “get” what you meant, without LLM.