Hi All, I've stumbled upon an open source project called Dograh. It poses itself as an "Open Source alternative to VAPI/Retell". Seems to be using Pipecat. Any of your familiar with it ?

Hey Community! Im finally going to finish my Grade 10 on April 4th, and Im looking for Opportunities, where I can learn the core of AI! So, Im Researching on Different Colleges for my Future Studies.. But it seems like I have to wait for Another 2 years just to get into a College which really focusses on AI.. I cannot wait that long, judging by the fact that AI is growing soo rapidly... I am open to self study, but I also want to go to a university where people are also learning about AI! If, in any of your connections can help me get into a University which really focusses on AI, then please let me know.. I want your help because I need to complete my 11th-12th and then get into a University, which is a problem.. So if anyone can help me connect with the directors of any University who are open to get me in then that would be really good! Im open to learn anything just to get the Admission(Like Maths Topics that are not taught in 10th Etc) I have been working on these AI Agents, Voice Agents and AI Automations for a while and Im interning at a Company, Working with Many Clients etc! But now, I cannot wait for another 2 years just to learn the Core of AI via Universities! So, Let me know if there's anyone who can help me! This is My LinkedIn: https://www.linkedin.com/in/muhammad-arhan-8753b0367/ Portfolio: https://arhan-ai.vercel.app/

What observability tools are others using with Pipecat or similar voice AI frameworks? I've built a production voice agent using Pipecat and currently track basic metrics (call duration, sentiment, summary, transcripts) in a custom dashboard. Tomorrow it's going in production so problem I think I can face is When errors will occur, debugging is painful. My current logging approach creates massive log files that are nearly impossible to analyze efficiently when tracking down issues.

Has any one built an voice bot without pipecat and livekit would love to connect with them I have built it and facing some issues in latency part My tech stack is openai llm , Deepgram for ASR and Azure for TTS and one telephony vendor which connects everything

What do you usually track for call metrics? duration, sentiment, rate of booking vs inquiries (if applicable), if caller ended call prematurely. Do you think it is important to track if caller always interrupts the agent and doesn't let the agent finish talking? Am thinking that's a sign the agent is talking too much. But right now I'm having a hard time getting that part right - it's counting more interruptions than the number of times the agent spoke. What else do you track?