Sharing a small but exciting milestone from my learning journey 🚀 Over the last few weeks, I’ve been deep into voice infrastructure and SIP, and I finally have a full working setup: 📞 Local Phone → SIP (from Signalwire) → FreeSWITCH → Voice Agent → Response back to the caller The FreeSWITCH server is running on a Debian server on DigitalOcean, and everything is now talking to each other smoothly — SIP, RTP, real-time audio, and AI responses. I’m currently working with a client, and initially we’re aiming to scale this setup to handle ~100 concurrent calls, which is pushing me to really understand: - SIP call flows - Audio streaming - Server performance & scaling - Latency trade-offs vs managed platforms Honestly, this stuff is challenging but insanely exciting. Every time a real phone call hits the server and the agent responds correctly, it feels like magic — but the earned kind 😄 Just wanted to share this win and keep building. If anyone here is working on voice agents, SIP, or FreeSWITCH — would love to connect and exchange notes 🤝

Looking for recommendation

Hello everyone, I’ve been developing Voice AI solutions for my clients using tools like VAPI, RetellAI, and others. Recently, I started exploring the Gemini Live API (Audio) and LiveKit agents to build more customizable solutions with greater control. One of my clients requested a POC using the Gemini API to integrate a voicebot widget on their website. I’m sharing a Loom demo below and would love to hear your thoughts on the audio quality and overall experience. https://www.loom.com/share/6f41e1c5b5724758be1be79a902b9a59

Hello everyone, I’m currently exploring the Livekit documentation and I’m stuck on the “Structured Output” and “Passing State” sections. For instance, let’s say the agent needs to ask five questions sequentially and send the structured output to an API endpoint. Which method would be the most appropriate and suitable in this scenario? @Darryn Campbell

Hey everyone! I’ve started experimenting with LiveKit Agents and documenting my journey in this repo: https://github.com/GreatHayat/livekit-agents I’ll continuously post my learnings here. Today I learned how to: - Create agents - Make tool calls - Implement agent handoff - Build workflows I also implemented a basic workflow that navigates users to the appropriate agent based on their age. Check it out and feel free to share any tips or feedback!