
DubSync
DubSync is an AI-powered platform designed for content creators and MCN (Multi-Channel Network) organizations to efficiently manage, translate, and distribute multilingual video content. The platform connects directly with YouTube, TikTok, and other content channels, allowing users to automatically sync uploaded videos, translate them into multiple languages using AI (speech-to-text, machine translation, voice synthesis), and publish them directly back to the desired platforms.
Design Goal:
To create an intuitive, streamlined experience for creators and media managers, reducing the time and complexity involved in multilingual video localization and distribution.
My Role:
Conducted the end-to-end design
Business Goals
1. Automated Video Translation
-
Provide a fast and automated video translation and dubbing workflow
-
Lower the cost and time investment for creators to translate and localize their video content.
2. Global Reach for Creators
-
Reduce barriers for non-native creators to reach international audiences
-
Help creators expand globally and grow their overseas follower base through multilingual content.
3. One-Click Platform Distribution
-
Support one-click distribution to platforms like YouTube and TikTok
-
Offer streamlined publishing and content management tools for individual creators and MCN agencies.
4. User Growth & Subscriptions
-
Attract users to adopt and subscribe to the platform
-
Drive user acquisition and platform engagement through compelling features and subscription-based services.
Research & Insight
Through stakeholder interviews, user behavior analysis, and competitor research, we generated original insights. These insights directly informed our core design directions and feature priorities.
Persona 1

Persona 2

Insight & Challenges
Insight
Simple Interface
VS
Complex Workflow
Balancing Automation with
Manual Control
Multi-language
and
Multi-speaker Content
Challenge
Make the translation workflow easy for beginners yet flexible for pros.
Users want “one-click AI,” but also need to review and adjust translations, subtitles, and voices.
Managing multiple languages, voices, and speakers can clutter the interface and confuse the user.
Design Focus
Offer one-click simplicity with optional step-by-step indicators in an intuitive UI.
Provide a smart default experience with optional deep customization for advanced users
UI components for speaker tags, language toggles, and voice selection that remain usable
Design Delivery
After gaining sufficient understanding and insights, I began the design process by breaking the project into smaller, manageable pieces. Each piece went through a cycle of analysis, wireframing, UI design, review, and iteration.
Design Roadmp

User Flow

Logo Design

Core Experience Screens




Design System (Parts)
