Case study · Voice AI · Web app
Intervue AI
Real-time AI interviews with 80% lower voice costs and 30% faster setup.
An AI interview practice platform where students simulate technical interviews in real time with a voice interviewer, on topics they choose.
- Built at
- Nexium
- Role
- Full-Stack Developer Intern
- Timeline
- Jul – Aug 2025
The challenge
Students preparing for technical interviews rarely get realistic practice: a live interviewer, questions for their domain, and a history they can review.
What I built
- Real-time voice interviews with domain-specific questions generated from the chosen topic and preferences.
- The backend logic behind the interviewer, including dual-role authentication, on LiveKit with Deepgram speech-to-text, Cartesia text-to-speech and a DeepSeek LLM.
- User profiles and interview history on Supabase, with a Next.js front end.
Results
- 80%lower voice costs
- 30%faster interview setup
Tools
- Next.js
- LiveKit
- Deepgram
- Cartesia
- DeepSeek
- Supabase
Want something similar? See voice ai agents →
More case studies
Voice AI · MelonLabs
WordBuddy AI
Shipped to Google Play with 80% lower conversational-AI costs.
Read the case study
AI automation · 16x9.ai
AI Content Automation Engine
Cut content production time 95% with four chained n8n workflows.
Read the case study
AI engineering · Text-to-CAD
NL-CAD
Plain English to CAD models: 46/46 eval cases pass at about $0.01 each.
Read the case study