⚡today we're launching lipsync-1.7.0-beta
an experimental state-of-the-art video-to-video lipsync model that generates more natural teeth and accurate skin tones
also generates ~1.5x faster than 1.6.0 and ~2x faster than 1.6.1 👀
available now – also through our new discord
⚡ launch + monetize your own AI dubbing app in <30 mins
drop a YouTube link + translate videos w/ perfect lip-sync
curious? we open sourced the whole repo 🚀
try it out / clone it here 👇
⚡️its official: we got into
@ycombinator
🙏
the last 4 weeks have been a blessing
yc w24 + 2 world renowned professors joining as advisors + 6k dev signups / 120+hrs of video generated in a single month
and we're just getting started
curious? check out what else is new👇
⚡️introducing visual dubbing w/ sync.
our api syncs the lips in a video to a new dubbed audio track – no more bad / misaligned dubs
now everyone can experience content like it was made for them in their native language
check out who we are + how it works 👇🧵
⚡launch your own AI dubbing app w/ lipsync in <30mins — now w/
@replit
our OSS repo is powerful, but complex
so we launched a repl — no devops, minimal setup 🚀
where we're born should never hold us back – we're making tools like this more accessible to everyone, everywhere👇
⚡ introducing sync-v1.5.0 – a stable model w/ premium lipsync across high angles / side profiles
available to all users now :)
this week we also:
- open sourced an AI dubbing app 🌍
- launched sync-v1.5.1-beta: an experimental build w/ more natural lip shapes / skin tones
-
⚡we launched a major speedup – lipsync a 15 min video < 45 mins
over the last week we also:
- launched an open source repl for AI dubbing w/ lipsync
- revamped our dev docs + API experience
- upgraded limits on file size and length (1hr max, up from 5 mins) 💪
we rebuilt our
⚡️in the last 2 weeks 3000+ devs used our api / playground to lipsync over 6000+ videos
this is up from 1k devs / 2k vids since our last changelog
this sprint we're rolling out an updated model w/ higher lipsync accuracy + fewer artifacts
check out what else is new👇
⚡lipsync-1.5-beta is live
the past few weeks were wild:
– our team moved to SF + setup the hacker house
– kicked off
@ycombinator
w24 batch
– launched an updated lipsync model + subscriptions
– crossed 10k+ users / 160hrs+ generated weekly 🚀
catch up w/ us in sync.log 004 👇
🚀 quick ship: sync-1.5 in beta
just released beta access to an updated lipsync model
~40% better lipsync accuracy + reduced bounding box artifact
try it out 👇
try it out for yourself and let us know what you think
if you have any questions join our slack channel / raise an issue on github
o/w – just dm
@therealprady
:)
we're excited to have
@therealprady
give a sneak peak of our new synchronizer model tomorrow
we've been busy building, but we're looking forward to showing you all the fruit of our labor
see you soon.
sync-1.7.0 can bring new life to old content
charlie chaplin was able to finally find his voice 🎩
lipsync any content using our simple web playground 🪄🛝
upload your video / translated audio + lip-sync the speaker to the new audio track
your first 5 mins of video generation every month is free
sign up here:
check how how I translate + visually dub Tim Ferris into Spanish
imagine a world where any video and any character can be repurposed + remixed to tell entirely new stories
eg. helping charlie chaplin find his voice 📣
most lipsync models can't do side angles / profiles very well
our models are learning accurate sync from multiple angles – moving beyond a talking head looking into a camera
⚠️ our production servers are currently down
we saw suspicious activity on our cloud account, we're taking precautions / making changes we're debugging now
we should have the service back up soon. will keep y'all up to date.
appreciate your patience 🙏 we're all hands on deck
ATTENTION HEADS – EP 9.0
@0xSamHogan
and I sit down with
@therealprady
, cofo + CEO of Sync, a real time lip-syncing API.
We discuss:
- Personalized ads
- Challenges of building a foundational model
- The paper I saw but didn’t read (a model to detect smells)
LINK ->
we're back online 👌
seeing a few users in different geos still not able to upload audio / video pairs to our app
we have a workaround in the discord^ if you're affected join and we'll help you out