Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
What is this?
Less
More
Memberships
Open Source Voice AI Community
763 members • Free
4 contributions to Open Source Voice AI Community
10h •
Voice agent observability with tracing
Are you using tracing in your voice agent? I thought about this today, because The team at LangChain built voice AI support into their agent debugging and monitoring tool, LangSmith. LangSmith is built around the concept of "tracing." If you've used OpenTelemetery for application logging, you're already familiar with tracing. If you haven't, think about it like this: a trace is a record of an operation that an application performs. Today's production voice agents are complex, multi-model, multi-modal, multi-turn systems! Tracing gives you leverage to understand what your agents are doing. This saves time during development. And it's critical in production. You can dig into what happened during each turn of any session. What did the user say and how was that processed by each model you're using in your voice agent? What was the latency for each inference operation? What audio and text was actually sent back to the user? You can also run analytics using tracing as your observability data. And you can use traces to build evals. Tanushree is an engineer at LangChain. Her video below shows using a local (on-device) model for transcription, then switching to using the OpenAI speech-to-text model running in the cloud. You can see the difference in accuracy. (Using Pipecat, switching between different models is a single-line code change.) Also, the video is fun! It's a French tutor. Which is a voice agent I definitely need. How to debug voice agents with LangSmith (video): https://youtu.be/0FmbIgzKAkQ LangSmith Pipecat integration docs page: https://docs.langchain.com/langsmith/trace-with-pipecat I always like to read the code for nifty Pipecat services like the LangSmith tracing processor. It's here, though I think this nice work will likely make its way into Pipecat core soon: https://github.com/langchain-ai/voice-agents-tracing/blob/main/pipecat/langsmith_processor.py
0
0
21d •
Who has built extremely scalable Voice AI System with LIvekit & Pipecat
I mean a system where one can do 10k calls per day. Has anyone built a system like this using livekit and pipecat. did you do it without using our own GPUs ?
2 likes • 16d
Which part of the scaling are you thinking about? For inference, most people that are doing 10k calls per day are using first-party, hosted services for STT, LLM, and TTS. You definitely can host your own models, but for two reasons, most people are not. First, the open weights models are still less capable than the commercial models. (Though I think that will change.) And second, it's actually more expensive to host your own models than to use the first-party, hosted, APIs until you are significantly bigger than 10k calls a day. For hosting the voice agent itself, the basic answer is that you need to get various bits and pieces of Kubernetes auto-scaling set up for your specific use case and cloud provider. (You can also look and see if Pipecat Cloud fits your needs. It's "docker push for voice agents".)
22d •
Voice AI without pipecat or livekit
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
2 likes • 16d
It's great to build things to learn! If there are latency issues that I can help you think through/diagnose, very happy to do that. Typical things that contribute to latency are: - using WebSockets instead of WebRTC (for edge-to-cloud, but this is probably not your case since you mention telephony), - long network round trips between all your providers (you want your voice agent very close to where your telephony provider terminates the PSTN, and to all your inference providers) - TTFT variance from your providers (you want to build observability tooling into your agent so you can measure and track this), - configuration parameters for Deepgram, etc - turn detection configuration - not streaming between models
Nov 8 •
Special Welcome!
A special welcome to @Kwindla Kramer CEO of Daily (the team behind Pipecat)! I’m a big fan of his work and so glad to see him join this community. Make sure to follow him on LinkedIn!
4 likes • Nov 10
Nice to see everyone here! Looking forward to hearing about what everyone is working on.
1-4 of 4
Active 10h ago
Joined Nov 7, 2025