Lemon Slice Live

AI

video avatar generation

SHOW HN2025

195points
84comments
#340of 3,837 in 2025
Top 9%of 2025 by points

How HN took it

CuriousMostly questions and neutral comments

19 positive, 35 neutral or asking, 3 mixed, 5 critical, out of 62 comments about the project. Thread score +0.27.

Design: 3 for, 2 againstExecution: 4 for, 0 againstPerformance: 2 for, 2 againstIdea: 2 for, 0 againstPricing: 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

  • Real-time video chat feels impressively natural

    From 3 comments
    • This is impressive. The video chat works well. It is just a hair away from a very comfortable conversation. I'm excited to see where you have it a year from now, if it turns out…
      zebomon on HN
    • Really cool stuff. It felt strangely real. Impressive!
      wouterjanl on HN
    • This is very impressive. Any details about model architecture and size? Input and output representation? How does voice work? You mentioned Deepgram. Does it mean you do…
      lostmsu on HN
  • Fun demo with well-known characters

    From 2 comments
    • this was overall fun. better than expected. i'm an office fan so tried dwight and michael scott. i hope you folks get better at this. excited to see where you get in the next 12…
      anishsikka on HN
    • Max Headroom lives !
      aorloff on HN

Objections

  • Latency of 3-6 seconds makes conversation awkward

    From 2 comments
    • The maker's post
    • This is impressive. The video chat works well. It is just a hair away from a very comfortable conversation. I'm excited to see where you have it a year from now, if it turns out…
      zebomon on HN
  • Email signup wall before trying the demo

    From 2 comments
    • If you could lower the email signup for a few hours, that'd be nice. I'm not going to sign up for yet another service I'm unsure about.
      tetris11 on HN
    • "Try it now live" and then request me to enter my email. I'll pass thanks.
      doublerabbit on HN
  • Use of copyrighted characters raises IP concerns

    From 2 comments
    • So basically the old open-source live-portrait hooked up with audio output. Was very glitchy and low res on my side. btw: Wondering if it's legal to use characters you don't have…
      mentalgear on HN
    • A really compelling experience. It seems clumsy to use copyrighted characters in your demos. Seems to me this will be a standard way to interact with LLMs and even companies -…
      andrewstuart on HN
  • Low resolution and glitchy output

    From 1 comment
    • So basically the old open-source live-portrait hooked up with audio output. Was very glitchy and low res on my side. btw: Wondering if it's legal to use characters you don't have…
      mentalgear on HN

Requests

  • Faster response latency

    From 2 comments
    • Glad you like it! IMO, biggest things to improve on are 1) time to video response and 2) being able to generate more complicated videos (2 people talking to each other, a person…
      sid-the-kid on HN
    • Thank you! Very much agree that we need to improve speed to make the conversation more comfortable. Our target is <2sec latency (as measured by time to first byte). The other…
      lcolucci on HN
  • Web embeddable version

    From 1 comment
  • API access

    From 2 comments
    • This is just brilliant. Hope you succeed, so that eventually I get an API to play with.
      ashishact on HN
    • Nice! Thanks for sharing. I hadn't seen that paper before. Looks like they take in a real-world video and then re-generate the mouth to get to lip synch. In our solution, we take…
      sid-the-kid on HN

Questions

  • Model architecture and size

    From 1 comment
    • This is very impressive. Any details about model architecture and size? Input and output representation? How does voice work? You mentioned Deepgram. Does it mean you do…
      lostmsu on HN
  • Cost of GPU inference

    From 2 comments
    • Nice! What infra do you use for inference? I'm wondering what the cost-effective platforms are for projects like this. GPUs on AWS and Azure are incredibly expensive for personal…
      dheera on HN
    • How much would this demo cost you from the HN traffic if you don't mind me asking?
      ivape on HN

Alternatives named

  • HeyGen

    From 1 comment
  • Tolan

    From 1 comment
  • character.ai

    From 1 comment
    • Hey, I tried this and enjoyed using the demo - looks really cool! Just curious how it compares to what character.ai recently put out as well
      snappyleads on HN
  • LivePortrait

    From 1 comment
    • So basically the old open-source live-portrait hooked up with audio output. Was very glitchy and low res on my side. btw: Wondering if it's legal to use characters you don't have…
      mentalgear 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/43785044)