PineVoice Smart Speaker - PINE STORE
pine64.com
Features: 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
  • hanke@feddit.nuEnglish
    25·
    6 天前

    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.

    • MalReynolds@slrpnk.netEnglish
      9·
      6 天前

      I love fully local stuff, but the LLM part seems very expensive. Even for such a simple thing as managing our lights and music.

      So, the simple things should just be voice command (not recognition, limited vocabulary), <wakeword> kitchen light on, what’s todays weather (assuming you automatically download it and have it there, needs TTS like whisper). That can run on a recent potato. Somewhat more complex things need full voice recognition e.g. Play me x songname by y artist. Laptop CPU should handle that fine. You’ll only need a full LLM for more general inquiries, e.g.<wakeword> What mess has Trump made today?, which will need web access seeing as small LLMs don’t have a lot of world knowledge (although you can self host Wikipedia and point it at that).

      If you have a desktop computer and a GPU with 16+GB VRAM (or even smaller using RAM and a MoE LLM) that’ll do the job with reasonable smarts e.g. Qwen 3.6 35BA3B, Gemma 4 12B or 26BA4B. You may have to wait a minute or two. Mine pulls around 55W at idle (7800XT) and does double duty as a NAS and gaming rig, or you can have it sleep most of the time and let the laptop wake it up when necessary.

    • P03 Locke@lemmy.dbzer0.comEnglish
      2·
      5 天前

      I love fully local stuff, but the LLM part seems very expensive. Even for such a simple thing as managing our lights and music.

      Yeah, this is something I found out when I hacked my Amazon Echo and put LineageOS on it. I like the new interface that isn’t constantly advertising Amazon bullshit as a screensaver, but it doesn’t have a GPU, so attempting to put any sort of voice component takes many seconds to try to process.

      And in this post-memory-crisis economy, it’s not quite the right time to buy a dedicated LLM processing rig for my house. But, this really needs to be the route in the future. Or just install a NPU on this speaker itself. Phones already do this, and it’s been the standard since 2017.

    • inari@piefed.zipEnglish
      2·
      6 天前

      Get a Strix Halo box to be your headless AI server

      They’re around 4k USD these days though…

      • i_love_FFT@jlai.luEnglish
        1·
        6 天前

        At this price point, there are also DHX Spark on the Nvidia side… I don’t know how they compare, though. Our software tech lead got one at work to test if it can reduce cloud expenses!

        • Scott@sh.itjust.worksEnglish
          2·
          6 天前

          I tried to get a Asus GX10 (DGX Spark from Asus), first unit was boot looping, replacement got through OOBE then failed to mount the drive and kernel panicked.

          I got my money back.

          • i_love_FFT@jlai.luEnglish
            1·
            6 天前

            Oh, good to know! I’m currently running AI stuff on my RTX3070 and it barely fast enough to be acceptable…

            However it’s nice to be able to ask HA to “turn off the lights close to the TV” without having to be hyper specific!

    • muusemuuse@sh.itjust.worksEnglish
      1·
      6 天前

      I’m thinking the same thing. I hate the idle power draw of my home server and want to migrate back to arm but have the x86 as a fallback node for games in whales and jellyfin transcodes, but it just doesn’t make sense to wake and sleep constantly for speech recognition.

    • 0x0@infosec.pubEnglish
      1·
      6 天前

      http://www.orangepi.org/html/hardWare/computerAndMicrocontrollers/details/Orange-Pi-6-Plus.html

      https://www.notebookcheck.net/Orange-Pi-6-vs-Raspberry-Pi-45-TOPS-AI-dual-2-5-Gbit-LAN-LPDDR5-and-dual-PCIe-4-SSDs.1323900.0.html

      Maybe something like this could work for you? (If you actually can find it in stock anywhere lol)

      Ai on arm is getting better and better, ive tried it on a radxa 5b and got almost ok chat speed for an 8b model, and that is only 6 tops