Services
Voice AI agent development
Real-time voice agents that talk to your customers, learners or candidates, and stay affordable at scale.
I build real-time voice agents that hold natural conversations with your customers, learners or candidates, and stay affordable as usage grows. I've shipped a voice tutor in a live Google Play app, an AI receptionist that books appointments, and a real-time AI interviewer.
A good fit if you're…
- EdTech products that need a speaking tutor
- Clinics, agencies and service businesses that miss calls or want 24/7 booking
- Hiring and training platforms that run interviews or role-play
- Teams whose voice prototype works in a demo but is too slow or expensive in production
What you get
- Tutors, receptionists and interviewers
- Speech-to-text, LLM and TTS pipelines tuned for latency
- Booking, CRM and knowledge-base integrations
- Latency and cost tuning: response caching and the right provider for each step
- Deployment, monitoring and a clean handover
How we'd work together
- 01Discovery callWe talk through the problem, your users and what success looks like.
- 02Scope & fixed quoteYou get a clear plan, milestones and a fixed price for the first build.
- 03Build with weekly demosYou see working software every week, not a big reveal at the end.
- 04Launch & supportI ship to production, hand over cleanly and stay on for fixes and next steps.
Ways to work together: Fixed-scope build, Monthly retainer, Consulting call.
Case studies
Voice AI · MelonLabs
WordBuddy AI
Shipped to Google Play with 80% lower conversational-AI costs.
Read the case study
Voice AI · Web app
Intervue AI
Real-time AI interviews with 80% lower voice costs and 30% faster setup.
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 studyTools I use
- LiveKit
- Vapi
- Deepgram
- ElevenLabs
- Cartesia
- Gemini
- DeepSeek
Questions
Which voice platform do you use?
It depends on what you need. Managed platforms like Vapi get a receptionist live quickly; a custom LiveKit pipeline with Deepgram, an LLM and ElevenLabs or Cartesia gives more control over latency and cost at scale.
Can the agent book appointments and use our information?
Yes. The receptionist built for 16x9.ai answers from an Airtable-backed knowledge base, books appointments and routes calls.
How do you keep running costs down?
By caching repeated answers and choosing providers per task. On WordBuddy AI this cut conversational-AI costs 80% with no drop in answer quality.
Other services
- AI automation & agentsWorkflows and agents that take repetitive work off your team, from research to publishing.
- AI product buildsFrom idea to a shipped, full-stack AI product: web, mobile and the backend behind it.