1. The Identified Problem
Personal budgeting tools impose excessive manual friction and overlook cash-heavy, informal multi-wallet habits across West Africa, causing users to abandon spreadsheets within days.
budgetvox-app.sinda.pro
2. Solution Engineered
A voice-native mobile application powered by a proprietary AI correction loop: users speak out their day, AI extracts multi-wallet expenses (Cash, MTN MoMo, Wave) and aligns theoretical balances with physical money without shame or complex math.
3. Results & Measurable Impact
Landing page and waitlist live on budgetvox-app.sinda.pro; the mobile app is in final internal testing before the beta opens: Deepgram Nova-3 voice transcription (< 300 ms latency) and structured AI expense extraction.
My role
- Product idea, requirements document (PRD) and MVP scope: voice input, AI extraction and the balance correction loop.
- Architecture: Flutter mobile app, FastAPI API and Supabase (PostgreSQL, authentication).
- Voice pipeline: Deepgram transcription with fallback providers, LLM expense extraction and monitoring of silent failures.
- Security: per-user data isolation (RLS), token verification in the API, full data erasure when an account is deleted.
- Landing page, waitlist and automated tests (Flutter and pytest).
Key Figures & Milestones
90% voiceHands-free budgeting without tedious forms
< 300 msUltra-low transcription latency with Deepgram
Multi-walletSeamless Cash, MTN MoMo, Wave reconciliation
Interface Gallery & Previews
Click any preview to inspect it in full screen view.
Technology Stack
- Flutter
- FastAPI
- Supabase
- Deepgram Nova-3
- OpenRouter
- Sentry