Shankhadeep Dey

Shankhadeep Dey

sync-3sync-3
Making Sync Better
All activity
sync-3 is a 16B parameter AI lip sync model that doesn't just move lips, it understands performances. Built on a global understanding of a person across an entire shot, it generates all frames at once instead of stitching isolated snippets. It handles what breaks every other model: close-ups, occlusions, extreme angles, low lighting - all while preserving the emotion of the original performance across 95+ languages in full 4K. Try it out at sync.so, via API, or in Adobe Premiere.
sync-3
sync-3Studio-grade AI lip sync and visual dubbing
A starting point for anyone who wants to create their own video editor! Features pre-built components for timeline, interactive canvas, fonts, captions, asset uploads, rendering and more. It's the best of Remotion in one template!
Remotion Editor Starter
Remotion Editor StarterA boilerplate for building your own video editor
Easily navigate any airport with personalised flight updates, tips and a directory of all shops, restaurants and lounges.
AirWalkerDiscover all airport amenities at your fingertips
Remotion Lambda allows you to render Remotion videos (written in React) on your self-hosted AWS Lambda function.

By dividing the video into many chunks and spawning many Lambda functions, videos are rendered much faster than they would on a single machine.
Remotion Lambda
Remotion LambdaA distributed video renderer