I find the popular real-time AI voice solutions (Fin, et al) difficult to integrate with existing call flows, often requiring a rip and replace mentality. Not to mention they can be a bear to setup. What I wanted was a native way to "plug" real-time AI into our existing PBX without any (or very minimal) configuration.Hi HN! My name's Kiern and I've been working on Leilani (https://leilani.dev),...
We built a SIP user agent that registers to any PBX just like a soft-phone and streams audio to OpenAI’s real-time API. No SIP trunking, call forwarding or unintegrated voice systems. Leilani behaves like a normal extension… because it’s just a normal SIP extension.How it works- Implements bog standard SIP over TCP to connect just like a normal desk phone or spftphone. - Streams RTP (mu-law)...
We’ve built an 802.1X platform that authenticates clients via external Identity Providers (Google, Azure, etc.) using OIDC to provision user accounts. Users enroll on a self-service page, complete the OIDC flow, and generate a username/password to authenticate. We continuously use the refresh token to re-verify users.Why did we build this? Many RADIUS services push EAP-TLS, which is great but...
I like to stick to quiet backroads and nothing currently on the market does a good job of hinting at what will be a quiet/less traveled road.
Good luck!