I built an open-source, self-hosted take on ElevenLabs' Reception.ai
The phone rings at a dental clinic while everyone's hands are busy. Nobody picks up. The caller books somewhere else. Frontdesk.ai is an open-source AI receptionist that picks up instead. It answers the call, books the appointment against a real calendar, answers questions from the business's own website, and leaves a transcript, a recording and a summary behind. Code:…
Frontdesk.ai is an open-source AI receptionist that can pick up phone calls instead of a human. It answers the call, books appointments against a real calendar, responds to questions from the business's website, and leaves a transcript, recording, and summary behind. The project is inspired by Reception.ai, an open-source AI receptionist from ElevenLabs, but is written from scratch and is an independent project not affiliated with ElevenLabs.
It runs on your own system using Docker Compose. The software answers calls in a natural voice through WebRTC audio, a voice worker, speech-to-text, an LLM with tools, and text-to-speech. It has three tools: check_availability, book_appointment, and search_knowledge. The stack includes Next.js 16, Supabase for data and auth, LiveKit for LiveKit rooms, Groq and Fish Audio for voice, BullMQ on Redis for background jobs, and front-end technologies like Tailwind CSS and shadcn/ui.
Frontend and background tools are swappable. The project is multi-tenant, secure with row-level security, and no inbound phone calls yet.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
