01
Challenge
LOVO AI’s Genny turns text into lifelike voiceover in 500+ voices across 100+ languages — with a built-in video editor, AI writer, subtitles and voice cloning in one workspace, used by 2M+ creators. The main delivery challenge was to give users powerful automation with clear feedback, predictable states, and guardrails around model behaviour, while keeping Write, Voice, and Sync consistent across the complete journey. We framed the engagement around the smallest production-worthy flow first, then expanded the scope without weakening the underlying component and data model.
02
How we built it
We began by mapping the user journey and the boundaries of the AI: what context it receives, what it may return, and where deterministic application logic must stay in control. We then built Write, Voice, and Sync as small end-to-end slices, connecting the interface to the data and model layers early so the team could test real responses instead of static mock-ups. Prompt, validation, and fallback behaviour were refined alongside the product UI. The main implementation used Next.js (App Router), React, TypeScript, and Tailwind CSS, with typed contracts keeping the JavaScript stack consistent across the product.
03
Delivery
The delivered scope brought Write, Voice, Sync, and Caption into one coherent production-ready product experience. Model output, product logic, and user feedback are separated clearly, which makes the AI easier to evaluate and evolve. For LOVO AI, the practical result is a product that communicates its value quickly while giving the team a maintainable base for continued delivery in ai & agents.
