Full Stack Engineer – React Native + Local Audio Models (Global OK)

Job ID: 39543540

Budget: $250 – $750 USD

We're hiring a freelance full stack engineer to help build an offline-first mobile app for real-time voice translation. This is a focused, early-stage build—small in scope, but with the potential for long-term work.

The MVP will be a native app for iOS and Android, built in React Native or Flutter, and will use local AI models for speech-to-text, translation, and voice output. No PWA. No user login. No cloud dependencies.

What You’ll Build:
- A mobile app with offline voice-to-voice translation
- Local STT integration (e.g., Whisper or similar)
- Local translation model (e.g., MarianMT or similar)
- Local TTS (e.g., eSpeakNG or RHVoice)
- A simple, clean UI and smooth UX for two-person back-and-forth translation
- Audio segmentation logic based on pause detection

Ideal For Developers Who:
- Are experienced with speech interfaces or audio-first apps
- Can work independently and deliver solid results on a tight budget
- Like working lean and efficiently
- Have shipped mobile apps to production before

Tech Stack (Preferred):
- React Native (or Flutter if justified)
- Whisper STT (or equivalent)
- MarianMT or local translation model
- eSpeakNG / RHVoice (or other local TTS options)
- GitHub

Skills Required:
- Mobile App Development
- Local model integration (STT, TTS, Translation)
- GitHub for version control
- Clean architecture, testing, and documentation

Scope + Compensation:
- Freelance only — not a salaried position
- Budget is tight, but payment is guaranteed
- MVP expected in 5–10 work days depending on experience
- Future milestones possible if MVP succeeds
- Engineering spec and PRD available after NDA

To Apply, Please Send:
- 1–2 links to mobile apps you’ve shipped (GitHub or live)
- Your city, time zone, and availability
- Your freelance rate and minimum engagement
- A short note on your experience with local models or audio features