Rehan A.

I build real-time voice agents that sound natural and work in production. I have a PhD and post-doc in speech and language processing, and 10+ years in ASR, TTS and audio-visual AI. What I deliver: - Voice agents on LiveKit and VAPI, wired to n8n, calendars and CRMs, covering booking, lead capture and call handoff - Speech models: Whisper and wav2vec2 for ASR, StyleTTS2 and Orpheus for TTS, plus diarization and audio quality testing - Conversational avatars with lip-sync (Rive and LiveKit) - LLM agents and RAG using LangChain and LangGraph Top Rated with a 100% Job Success Score. I work in the open: you get a working demo early, clear milestones, and a handover guide. Tell me what your callers or users should experience, and I'll tell you how I'd build it.