RealtimeVoiceChat

AI

voice assistant

SHOW HN2025

524points
227comments
#64of 3,837 in 2025
Top 2%of 2025 by points

How HN took it

CuriousMostly questions and neutral comments

12 positive, 52 neutral or asking, 4 mixed, 18 critical, out of 86 comments about the project. Thread score -0.05.

Execution: 0 for, 10 againstDesign: 2 for, 3 againstPerformance: 1 for, 3 againstIdea: 2 for, 2 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

  • Interruption handling is impressive

    From 1 comment
    • This is very, very cool! The interrupting was a "wow" moment for me (I know it's not "new new" but to see it so well done in open source was awesome). Question about the…
      joshstrange on HN
  • Lightweight web front end and VAD implementation liked

    From 1 comment
    • Nice work, I like the lightweight web front end and your implementation of VAD.
      oldgregg on HN

Objections

  • Requires a CUDA GPU; hard to set up on Windows and Python versions

    From 1 comment
    • Every time I see these things, they look cool as hell, I get excited, then I try to get them working on my gaming PC (that has the GPU), I spend 1-2h fighting with python and…
      sabellito on HN
  • Speech voice quality sounds worse than leading voice AIs

    From 1 comment
    • It's fast, but it doesn't sound good. Many voice chat AIs are way ahead and sound natural.
      bufferoverflow on HN

Requests

  • Support for Mac or Raspberry Pi

    From 2 comments
  • Better TTS models such as Dia

    From 2 comments
    • Quite good, it would sound much better with SOTA voices though: https://github.com/nari-labs/dia
      fintechie on HN
    • Have you considered using Dia for the TTS? I believe this is currently "best in class" https://github.com/nari-labs/dia
      SillyUsername on HN

Questions

  • How interruptions handle short noises like 'mmk' or coughs

    From 1 comment
    • This is very, very cool! The interrupting was a "wow" moment for me (I know it's not "new new" but to see it so well done in open source was awesome). Question about the…
      joshstrange on HN
  • Whether multiple simultaneous clients are supported

    From 1 comment

Alternatives named

  • Sesame

    From 1 comment
    • Kind of surprised nobody has brought up https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice#demo It interacts nearly like a human, can and does interrupt me once…
      cannonpr on HN
  • Pipecat

    From 1 comment
    • Have you looked at pipecat, seems to be similar trying to do standardized backend/webrtc turn detection pipelines.
      dummydummy1234 on HN
  • Dia

    From 1 comment

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/43899028)