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

So, over the past few weeks - I've been neck deep into working with PIpecat, LiveKit and Vibe Coding. Mainly, I wanted to see what kind of milage I can get from Vibe Coding tools, and in order to test it - what's a better way than build a Pipecat/LiveKit implementation? So, I decided to examine 3 primary tools: - Claude Code - Using Sonnet 3.5 (using CLI) - OpenCode - Grok Code Fast 1 - Google Antigravity - Using Gemini 2.5 Below are my conclusions, split into several categories. 💵 Financials: Most expensive to use - Claude Code Least expensive to use - OpenCode 😡 Developer Experience: Best experience - Google Antigravity Worst experience - Claude Code 💪 Reliability: Most reliable - Claude Code Least reliable - OpenCode 🚅 Performance: Fastest planning and building - Google Antigravity Slowest planning and building - OpenCode So, overall - there is no "one tool to rule them all" here - and what I found out that each tool is really good at performing specific tasks. Here is what I've learned about how to "leverage" these tools in order to build something successful: - Planning can be performed with either OpenCode of Google antigravity. Google provides free developer credits for Antigravity, and their deep-thinking and reasoning engine, when applied to software architecture and design works very well. - Backend development with either ClaudeCode or Google Antigravity. When coupled with proper topic sub-agents, these are really powerful tools. For some odd reason, Claude Code is far more capable at handling complex architectures, while Google Antigravity leans towards the "hacker style" coding. - UI/UIX development - without any question, OpenCode did a better job. It was far more capable in spitting out hundreds of lines of working UI/UX code - even faster that Claude. However, if at some point it gets stuck on a specific UI component package, it may require Claude to show it the light - so pay attention to what it's doing. - Code Review, Security and Privacy - without any question, Claude is the winner here - with potentially the most extensive availability of sub-agent topic experts.

Hey guys , I hope you all are well . I am not sure if I am allowed to ask this question. But I am struggling with perhaps easy stuff for you . I tried so much but here my barrier is kicking in. I am not getting call ended events like transcripts or similar sensed to my webhook. Or precised: I am getting a message via webhook that a call has ended but always with missing transcripts. (I am using cartesia , deepgram etc.) Has anyone's idea why ? I can also share the codes if it's helpful . And another thing is , I don't get Vonage as phone provider properly working . (I am not using Twillio ) Has any one some secrets you can share with me ? Wish all happy Christmas Best Oli

Hello everyone, I want to build a dashboard where the client can see the logs of their calls: the type of call (inbound or outbound), the time and date, and other important information such as the transcription. My question is: in LiveKit, what would be the best approach to send this information to the backend? Should I rely on LiveKit webhooks/events, send everything when the session closes, or use another option?

So livekit just announced this which is big thing. now all agents can be built using livekit and no need to bother with vapi and their extreme restricitons: https://blog.livekit.io/announcing-agent-builder-a-pathway-to-code/