Pi-C.A.R.D

AI

voice assistant

SHOW HN2024

344points
92comments
#158of 3,515 in 2024
Top 5%of 2024 by points

How HN took it

CuriousMostly questions and neutral comments

8 positive, 27 neutral or asking, 0 mixed, 2 critical, out of 37 comments about the project. Thread score +0.19.

Idea: 3 for, 0 againstPrivacy: 2 for, 0 againstPerformance: 0 for, 2 againstDesign: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Privacy-focused offline alternative to Alexa

    From 3 comments
    • All I need is a voice assistant that: - RPi 4 can handle, - I can integrate with HomeAssistant, - is offline only, and doesn't send my data anywhere. This project seems to be…
      pawelduda on HN
    • I really like having a voice assistant that focuses on privacy first. I will definitely try it. always add a video to show how it works. Thank you
      8mobile on HN
    • I'm looking forward to trying this. Hopefully this gains traction, as (AFAIK) an open, reliable, flexible, privacy focused voice assistant is still sorely needed. About a year…
      ethagnawl on HN
  • Name and Star Trek theme well received

    From 2 comments
    • Pi-C.A.R.D is perfect. Read it 100% as Picard, and more recognizable that LCARS.
      rkagerer on HN
    • Extra kudos for the name - and extra extra for using the good old "Picard facepalm" meme. But seriously - the name got my attention, then I read the introduction and thought…
      rob74 on HN

Objections

  • Latency is high, about 5 seconds to start a response and 45 seconds for vision

    From 1 comment
    • Fully depends on the model, how much conversational context you provide, but if you keep things to a bare minimum, ~< 5 seconds from message received to starting the response…
      nkaz123 on HN
  • Wake word misdetection, the maker notes mis-heard versions of the wake word

    From 1 comment
    • The wake word detection is an interesting problem here. As you can see in the repo, I have a lot of mis-heard versions of the wake word in place, in this case being "Raspberry".…
      nkaz123 on HN

Requests

  • Run on a generic Linux box or a laptop or mini PC

    From 3 comments
    • Is it possible to run this on a generic linux box? Or if not, are you aware of a similar project that can? I've googled it before, but the space is crowded and the caveats are…
      knodi123 on HN
    • +1. That's the #1 feature I want in any "assistant". A question: does it run only on the Pi5 or other (also non Raspberry Pi) boards?
      squarefoot on HN
    • Thanks. My ideal use case would probably involve a mini PC, of which I have a few spares and most of them are faster and can be upgraded to more RAM than the Pi5, which…
      squarefoot on HN
  • Offload heavy processing to a home server

    From 1 comment
    • I have a decent home server, is there a system like this where the heavy lifting can be run on my home server but the front end piped to a ras-pi with speaker/camera, etc. ? If…
      BizarroLand on HN
  • Better text-to-speech than espeak

    From 1 comment
    • When I did a similar thing (but with less LLM) I liked https://github.com/coqui-ai/TTS but back then I needed to cut out the conversion step from tensor to a list of numbers to…
      t-vi on HN

Questions

  • Does it run only on Raspberry Pi 5 or other boards

    From 1 comment
    • +1. That's the #1 feature I want in any "assistant". A question: does it run only on the Pi5 or other (also non Raspberry Pi) boards?
      squarefoot on HN
  • How does the wake word work

    From 1 comment
    • how does wake word work? Does it keep listening and ignore if the last few seconds does not have the wake word/phrase?
      aci_12 on HN
  • Does it support languages other than English

    From 1 comment
    • I didn't see a mention of languages in the readme. Does this understand languages other than english?
      ghnws on HN
  • Can the model learn and keep memory beyond one conversation

    From 1 comment
    • How hard is it to make an offline model like this learn? The readme mentions a memory that lasts as long as each conversation which seems like such a hard limitation to live with.
      zenkalia on HN

Alternatives named

  • Home Assistant voice control

    From 1 comment
    • Have you checked out the Voice Assistant functionalities integrated into HA? https://www.home-assistant.io/voice_control/ NabuCasa employed the Rhasspy main dev to work on these…
      jhbruhn on HN
  • Rhasspy

    From 1 comment
    • Check out Rhasspy. You won't get anything practically useful running LLMs on the 4B but you also don't strictly need LLM-based models. In the Rhasspy community, a common pattern…
      baobun on HN
  • Mycroft

    From 1 comment
    • I'm looking forward to trying this. Hopefully this gains traction, as (AFAIK) an open, reliable, flexible, privacy focused voice assistant is still sorely needed. About a year…
      ethagnawl on HN
  • Willow

    From 1 comment
    • Funny, I just picked up a device for use with https://heywillow.io for similar reasons
      cmcconomy on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/40346995)