@googlestudents: Khoi, a PhD intern at Google, is solving a classic translation challenge: making lip movements match dubbed audio. His …
Summary
Google highlights PhD intern Khoi's research on synchronizing lip movements with dubbed audio to create natural-looking multi-language videos for YouTube.
View Cached Full Text
Cached at: 07/29/26, 03:53 AM
Khoi, a PhD intern at Google, is solving a classic translation challenge: making lip movements match dubbed audio. His research aims to bring seamless, natural-looking multi-language videos to YouTube viewers worldwide.
Learn more about a career in research at Google ➡️ https://t.co/wyd97cJJOW
AI at Google - Google Careers
Equal Opportunity
Google is proud to be an equal opportunity and affirmative action employer. We are committed to building a workforce that is representative of the users we serve, creating a culture of belonging, and providing an equal employment opportunity regardless of race, creed, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition (including breastfeeding), expecting or parents-to-be, criminal histories consistent with legal requirements, or any other basis protected by law. See alsoGoogle’s EEO Policy,Know your rights: workplace discrimination is illegal,Belonging at Google, andHow we hire.
Similar Articles
@GoogleDeepMind: 3.5 Live Translate can convert speech into over 70 languages and processes it as it’s streamed - while keeping tone, pa…
Google DeepMind announces Live Translate, a feature that converts speech into over 70 languages in real-time while preserving tone, pace, and pitch for more natural conversations.
@Huahuazo: The most annoying part of reposting overseas videos? Manually cutting subtitles, eye-straining translation alignment, and guessing audio sync—this workflow is so inefficient it makes you want to smash your keyboard. VideoLingo connects the entire process into an automated pipeline. It has 7k+ stars on GitHub and an MIT license, so it's reliable to use. …
VideoLingo is an open-source video translation, localization, and dubbing tool that uses WhisperX and AI to deliver Netflix-level subtitles and multilingual dubbing. It supports downloading via yt-dlp and multiple TTS options, helping video reposters automate the entire workflow.
How Descript engineers multilingual video dubbing at scale
Descript redesigned its translation pipeline using OpenAI reasoning models to optimize multilingual video dubbing at scale, achieving 15% increase in translated video exports and 13-43% improvement in duration adherence across languages by addressing the challenge of matching speech duration to video timing constraints.
@rwayne: Video translation has been cracked by a single Oxford postdoc. Kevin Lin, a postdoc at Oxford University, open-sourced Violin, a video translation tool that integrates speech recognition, LLM translation, and speech synthesis into an automated pipeline. It supports multilingual translation, personalized translation styles, and all-in-one video dialogue; it can turn academic reports into children's...
Kevin Lin, a postdoctoral fellow at Oxford University, open-sourced Violin, a video translation tool that integrates speech recognition, LLM translation, and speech synthesis into an automated pipeline. It supports multilingual translation and personalized styles, and provides three usage modes: Web, CLI, and Agent.
@KevinQHLin: IntroducingViolin — an Open-source Video Translation Skill. Video is the dominant medium on the internet, yet most high…
Violin is an open-source video translation skill that combines speech recognition, LLM translation, and speech synthesis into a seamless pipeline, supporting multilingual ASR, personalized translation, and interactive chat with video content.