Text to Speech: Voxa

AI voice generation from text with natural-sounding output

Project Overview

Voxa lets users turn written text into natural-sounding speech with AI-generated voices, making it easy to create voiceovers, spoken content, and audio-ready clips in seconds.

Designed and built Voxa as a production iOS app using React Native, Expo, and TypeScript with Supabase for backend services, plus Supabase Edge Functions to orchestrate secure text submission and AI-powered voice generation workflows. The core flow takes user-written text, transforms it into natural-sounding spoken audio, and returns a fast, clear playback experience focused on simplicity and output quality.

Localized the app in multiple languages, then shipped and optimized the App Store listing with multilingual metadata, screenshots, and ASO iterations, and launched a marketing site to support acquisition.

Key Achievements

Built an end-to-end text-to-audio generation flow with fast playback delivery

Implemented AI-powered voice generation focused on natural-sounding output quality

Designed a simple creation UX optimized for quick conversion from text to speech