{"id":79187,"title":"sync. – AI lip sync tool for video content creators","tagline":"from the team behind original Wav2Lip library ","body":"**TL;DR:** we’ve built a state-of-the-art lip-sync model – and we’re building towards real-time face-to-face conversations w/ AI indistinguishable from humans 🦾\n\ntry our playground here: \u003chttps://app.synclabs.so/playground\u003e\n\n**how does it work?**\n\n[ ](https://www.loom.com/share/a82317f622ec4e389387849a6c4a2073?sid=3f0b2b1e-4212-4940-bcca-b10aefeeda3e)\n\ntheoretically, our models can support any language — they learn phoneme / viseme mappings (the most basic unit / “token” of how sounds we make map to the shapes our mouths make to create them). it’s simple, but a start towards learning a foundational understanding of humans from video.\n\n**why is this useful?**\n\n_\\[1\\] we can dissolve language as a barrier_\n\ncheck out how we used it to dub the [entire 2-hour Tucker Carlson interview with Putin speaking fluent English.](https://vimeo.com/914605299)\n\nimagine millions gaining access to knowledge, entertainment, and connection — regardless of their native tongue.\n\nrealtime at the edge takes us further — live multilingual broadcasts + video calls, even walking around Tokyo w/ a Vision Pro 2 speaking English while everyone else Japanese.\n\n_\\[2\\] we can move the human-computer interface beyond text-based-chat_\n\nkeyboard / mice are lossy + low bandwidth. human communication is rich and goes beyond just the words we say. what if we could compute w/ a face-to-face interaction?\n\nmaybe embedding context around expressions + body language in inputs / outputs would help us interact w/ computers in a more human way. this thread of research is exciting.\n\n_\\[3\\] and more_\n\npowerful models small enough to run at the edge could unlock a lot:\n\neg.\n\nextreme compression for face-to-face video streaming\n\nenhanced, spatial-aware transcription w/ lip-reading\n\ndetecting deepfakes in the wild\n\non-device real-time video translation\n\netc.\n\n**who are we?**\n\n[ ](https://www.loom.com/share/42b332287f3d473196d1a0929099e3ea?sid=604edca5-f5ba-441a-9e23-d8e1f6ac5aa5)\n\n[**Prady Modukuru**](https://www.linkedin.com/in/prady-modukuru) **\\[CEO\\] |** Led product for a research team at Microsoft that made Defender a $350M+ product, took MSR research into production moving it from bottom of market to #1 in industry evals.\n\n[**Rudrabha Mukhopadhyay**](https://www.linkedin.com/in/rudrabha/) **\\[CTO\\] |** PhD CVIT @ IIIT-Hyderabad, co-authored wav2lip / 20+ major publications + 1200+ citations in the last 5 years.\n\n[**Prajwal K R**](https://www.linkedin.com/in/prajwalrenukanand/) **\\[CRO\\] |** PhD, VGG @ University of Oxford, w/ [**Andrew Zisserman**](https://scholar.google.com/citations?user=UZ5wscMAAAAJ\u0026hl=en), prev. Research Scientist @ Meta, authored multiple breakthrough research papers (incl. Wav2Lip) on understanding and generating humans in video\n\n[**Pavan Reddy**](https://www.linkedin.com/in/pavan-reddy-8bb85a67/) **\\[COO/CFO\\]** 2x venture-backed founder/operator, built the first smart air purifier in India, prev. monetizing sota research @ IIIT-Hyderabad, engineering @ IIT Madras\n\n**how did we meet?**\n\nPrajwal + Rudrabha worked together at IIIT-hyderabad — and became famous by [shipping the world’s first model](https://github.com/Rudrabha/Wav2Lip) that could sync the lips in a video to any audio in the wild in any language, no training required.\n\nthey formed a company w/ Pavan and then worked w/ the university to monetize state-of-the-art research coming out of the labs and bring it to market.\n\nPrady met everyone online — first by hacking together a viral app around their open source models, then collaborating on product + research for fun, to cofounding sync. + going [**mega-viral.**](https://x.com/therealprady/status/1680645510103977987?s=20)\n\nSince then we’ve hacked irl across 4 different countries, across the US coasts, and moved into a hacker house in SF together.\n\n![uploaded image](/media/?type=post\u0026id=79187\u0026key=user_uploads/587624/1beb86a1-5ea0-404a-aab7-ada7eff4f154)\n\n**what’s our ask?**\n\ntry out our playground and API and let us know how we can make it easier to understand and simpler to use 😄\n\nplay around here: \u003chttps://app.synclabs.so/playground\u003e","slug":"KbD-sync-ai-lip-sync-tool-for-video-content-creators","created_at":"2024-03-08T00:36:58.008Z","updated_at":"2026-04-23T10:27:05.566Z","total_vote_count":58,"url":"https://www.ycombinator.com/launches/KbD-sync-ai-lip-sync-tool-for-video-content-creators","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":29346,"name":"sync.","slug":"sync-2","url":"https://sync.so/","logo":"https://bookface-images.s3.amazonaws.com/small_logos/c534b008e7ff085ee7e32e819767b1f82d6d2396.png","batch":"Winter 2024","industry":"B2B","tags":[],"search_path":"https://bookface.ycombinator.com/company/29346"}}