Made a video walking through the AI-assisted development workflow I use for production voice AI projects. Quick context: I used this on a Vapi replacement project at a $4 billion unicorn. Within a couple of weeks, their engineering team had adopted the workflow without being asked — and they wanted me to present it division-wide. The video covers: - How I coordinate specialised AI agents for Pipecat, Vapi, and Twilio research - Building features that would normally take hours of documentation reading - Live implementation of JSON-based assistant configuration (swap providers via config file, no code changes) https://youtu.be/AG68VC_mOGY Happy to answer questions.

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 ?

Hi, Anyone working with Pipecat and Heygen interactive avatar? Heygen disconnects after 5 minutes of the session start while talking, not idle. Could not find a way around this. Heygen customer service recommends having activity_idle_timeout, but it doesn't work. It seems that this is a bug in Pipecat itself. Anyone found a way around it? heyGen = HeyGenVideoService( api_key=os.getenv("HEYGEN_API_KEY"), session=session, session_request=NewSessionRequest( avatar_id="Katya_Chair_Sitting_public", version="v2", quality=AvatarQuality.medium, activity_idle_timeout=1800 # 30 minutes ), ) Thanks.

Hey folks in the voice AI community, I've been grinding away on integrating Telnyx telephony with Pipecat for a custom customer request bot – an inbound voice assistant that handles real conversations(customer issues). My Pipecat playground (STT, LLM, TTS) is rock-solid locally... But Telnyx transport? It's been a battle. The WebSocket connects, VAD detects speech, but the AI just blanks on understanding me – like the 8kHz telephony signal isn't hitting STT right, causing silent or hallucinated transcripts. Tried GPT-4o-mini STT in another project and it butchered Polish language- and English; clearly need telephony-tuned STTs. I can list the key challenges I've wrestled with in Pipecat (v0.0.93) + Telnyx, plus quick notes on what I solved (spoiler: core understanding is still pending). My understanding is that Pipecat is still maturing in that domain. Anyone nailed a working Telnyx + Pipecat integration for real-time agents? How do you tune STT (Deepgram, OpenAi, AssemblyAI, or others?) to grok the Telnyx frequency without losing the plot? Would you be so kind to Share your setup or fixes? – this could turn into long-term collab gold. Cheers, Arek

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!