I'm fairly new to this but when I paired a custom LLM with Pipecat the latency wasn't what I was expecting. After some research I came across Ultravox and latency is top notch. But using it for a project in EdTech may end up making the business model less feasible... Does anyone else have experience with Ultravox or a custom build that is handling latency better?

I built a voice AI assistant for my website using Pipecat and Gemini's native audio model. People kept calling it trying to reverse-engineer how it works, so I just open-sourced the whole thing. It's a good starting point if you want to build your own web-based voice AI demo with low latency and multilingual support. Repo: https://github.com/askjohngeorge/askjg-demo-gemini-pcc System prompt: https://github.com/askjohngeorge/askjg-demo-gemini-pcc/blob/main/bot/prompts/demo_system_prompt.md You can try the live demo at https://askjohngeorge.com/demo (click the mic). Happy to answer questions if you have any.

Hey Guys! I'm fairly experienced with VAPI, but 100% new to open source voice AI. I'm currently looking to get deeper into that, and wondering what the state of the art/commonly used providers/models for STT, TTS, LLM, turntaking?, ... are, that are open source/hosted/usable in the EU. I had an advisory call today with a start-up that wants to integrate voice AI, and since they're in GER they need to be compliant and I want to recommend them a few good and solid options for their infra. Thank you already for letting me know your thoughts! Happy to learn! Cheers!