LemonSlice
AI
video avatar model
SHOW HN2026
133points
133comments
#494of 4,366 in 2026
Top 12%of 2026 by points
How HN took it
CuriousMostly questions and neutral comments
28 positive, 46 neutral or asking, 1 mixed, 14 critical, out of 89 comments about the project. Thread score +0.18.
Idea: 8 for, 6 againstPerformance: 4 for, 1 againstExecution: 2 for, 3 againstDesign: 1 for, 2 againstDocs: 1 for, 1 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
Impressive real-time quality and latency
From 3 comments
Wow this is really cool, haven't seen real-time video generation that is this impressive yet!
korneelf1 on HNThat's amazing. Feels like a major step ahead. No lag, very snappy. Outstanding work. Feels like those sci-fi shows where you can talk to Hari Seldon even though he lived like a…
slake on HNWow this is the most impressive thing I’ve seen on hacker news in years!!!!! Take my money!!!!!!
r0fl on HN
Much better than competing avatar products
From 1 comment
this is like Tavus but it doesnt suck. congrats!
swyx on HN
Objections
Photorealistic avatars enable deception and harm
From 3 comments
Absolutely Do Not Want. EDIT: Tell us what characters you want to see in the comments and we can make them for you to talk to (e.g. Max Headroom) Sure, that kind of thing is…
anigbrowl on HNThe primary purpose of generating real-time video of realistic-looking talking people is deception. The explicit goal is to make people believe that they're talking to a real…
zestyping on HNWhen you generate real-time video of realistic-looking talking characters, the definition of success is fooling people into believing they are talking to a real person when they…
zestyping on HN
Latency and turn-taking feel unnatural compared with speech-to-speech models
From 2 comments
This is so awesome, well done LemonSlice team! Super interesting on the ASR->LLM->TTS pipeline, and I agree, you can make it super fast (I did something myself as a 2-hour hobby…
armcat on HNI asked the Spanish tutor if he/it was familiar with the terms seseo[0] and ceceo[1] and he said it wasn't, which surprised me. Ideally it would be possible to choose which…
jonsoft on HN
Requests
Add Max Headroom and other characters
From 2 comments
You could add a Max Headroom to the hn link. You might reach real time by interspersing freeze frames, duplicates, or static.
wumms on HNAnd, just like that, Max Headroom is back: https://lemonslice.com/try/agent_ccb102bdfc1fcb30
sid-the-kid on HN
Open weights or local runnable model
From 2 comments
"we're releasing our new model" is it downloadable and runnable in local? Could I create a "vTuber" persona with this model?
mdrzn on HNwhere can I find the 20B model? it sounded like it would be open - but I am not sure with the phrasing...
dsrtslnd23 on HN
Speech-to-speech voice support such as PersonaPlex
From 1 comment
One thing I've learnt from movie production is actually what separates professional from amateur quality is in the audio itself. Have you thought about implementing personaplex…
pickleballcourt on HN
Questions
Is the 20B model open weights?
From 2 comments
I got really excited when I saw that you were releasing your model. > Today we're releasing our new model* - Lemon Slice 2, a 20B-parameter diffusion transformer that generates…
peddling-brink on HNwhere can I find the 20B model? it sounded like it would be open - but I am not sure with the phrasing...
dsrtslnd23 on HN
How does it differ from anam.ai?
From 1 comment
Have just tried it. Impressive. We are definitely moving into this space Questions what are the main differences between you and anam.ai ? They also do real time lip sync plus…
Obertr on HN
Alternatives named
Tavus
From 1 comment
this is like Tavus but it doesnt suck. congrats!
swyx on HN
anam.ai
From 1 comment
Have just tried it. Impressive. We are definitely moving into this space Questions what are the main differences between you and anam.ai ? They also do real time lip sync plus…
Obertr on HN
NVIDIA PersonaPlex
From 2 comments
One thing I've learnt from movie production is actually what separates professional from amateur quality is in the audio itself. Have you thought about implementing personaplex…
pickleballcourt on HNI asked the Spanish tutor if he/it was familiar with the terms seseo[0] and ceceo[1] and he said it wasn't, which surprised me. Ideally it would be possible to choose which…
jonsoft on HN
Sesame
From 1 comment
This is so awesome, well done LemonSlice team! Super interesting on the ASR->LLM->TTS pipeline, and I agree, you can make it super fast (I did something myself as a 2-hour hobby…
armcat on HN