Move your Vapi assistants to a self-hosted server with no platform fee
Hosted voice-agent platforms add a per-minute fee on top of what you pay your speech-to-text, model, voice and phone providers. OpenRing is an open-source (MIT) alternative that runs on your own machine and speaks Vapi's API, so you can move an account in a few minutes. 1. Start it You need Node.js 18 or later. Everything else, Python included, installs itself: npx openring The dashboard opens at…
OpenRing is an open-source alternative to hosted voice-agent platforms that runs on your own machine. It speaks Vapi's API, allowing you to move an account in a few minutes. To get started, you need Node.js 18 or later. The dashboard opens at http://localhost:8000, where you can choose a password and connect providers on the Providers page.
You can import your account, including assistants, squads, tools, and Twilio numbers, in one request using the curl command. The imported account lists any issues that prevent it from taking calls, such as unsupported providers. Importing again updates any changes. To test, open an assistant and press Test, then speak into your microphone.
Each call records its transcript, latency, and cost per provider. To point your client at the server, change your client's base URL to your server's address and update the voice webhook for each number to $PUBLIC_URL/twilio/voice. At this time, only Twilio has taken real calls, while other providers are in beta. The server runs Vapi's default limits of 10 minutes and 30 seconds of silence.
You are responsible for the server's uptime and compliance. A fully local, free stack is possible, but voice performance on a laptop CPU can be slow. For any issues, report them at https://github.com/elifalanrocha/openring/issues/16.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.