You have two routes, and TigZig runs a live open-source reference app for each - both wired to a real Postgres database (the demo queries a static snapshot of 1.5M cricket records, but the pattern is domain-agnostic: finance, retail, anything).
Build your own (see https://www.tigzig.com/realtime-voice-webrtc): a realtime model over WebRTC with function calling, plus a FastAPI layer for database connectivity. You get full UI control and a much lower per-minute cost, but the honest warning from building it: it is not plug-and-play. You will go deep into event flows, WebRTC and the API - it is a code-and-build journey. Drop in a vendor widget (see https://www.tigzig.com/realtime-voice-elevenlabs, built on ElevenLabs' conversational widget): plug-and-play, excellent performance, running in minutes - but limited UI customization unless you adopt their SDK, and it cost several times more per minute.
Two caveats. Pricing and models move fast in realtime voice, so check current rates rather than trusting any figure you read (including older ones on this site). And secure it properly - the reference apps use basic domain whitelisting, which is fine for a demo, not for production. Because it uses function calling, the agent can also act, not just answer.
Both apps are open source. Write-up: https://www.tigzig.com/post/realtime-voice-ai-openai-webrtc-implementation-live-app-open-source. Related: where to get a free Postgres database https://www.tigzig.com/agents-faq/where-to-get-a-free-postgres-database and querying a database in plain English https://www.tigzig.com/agents-faq/how-to-query-a-database-in-plain-english.
← All Agents FAQ