I'm currently in Vietnam, Hanoi and wanted to see if I have any AI Voice Agent developers from vietnam in this community. If yes just drop a comment I would love to connect with some of you.

Hi everyone, I'm building a specialized voice assistant using **Pipecat Flows v0.0.22** and running into a frustrating issue with phone number collection that I can't seem to solve. ### The Stack - **Framework:** Pipecat Flows v0.0.22 (Python) - **STT:** Deepgram Nova-3 (Polish `pl`) - **TTS:** Cartesia (Polish voice) - **Transport:** Local WebRTC (browser-based, no telephony yet) ### The Problem When I dictate a 9-digit Polish phone number (e.g., "690807057"), the assistant receives partial fragments and processes them individually instead of waiting for the full number. For example, if I say "690... 807... 057" (with natural pauses), the bot splits it into: 1. "6" -> sent to LLM -> LLM complains "Received only 1 digit" 2. "980" -> sent to LLM -> LLM complains 3. "5" ... and so on. ### What I Have Tried I've gone through the documentation and tried several fixes, but the "defragmentation" issue persists. 1. **Deepgram Configuration (Current Setup):** I've configured the `LiveOptions` to handle phone numbers and utterance endings explicitly: ```python options = LiveOptions( model="nova-3", language="pl", smart_format=True, # Enabled numerals=True, # Enabled utterance_end_ms=1000, # Set to 1000ms to force waiting interim_results=True # Required for utterance_end_ms ) ``` *Result:* Even with `utterance_end_ms=1000`, Deepgram seems to finalize the results too early during the digit pauses. 2. **VAD Tuning:** - I tried increasing Pipecat's VAD `stop_secs` to `2.0s`. - *Result:* This caused massive latency (2s delay on every response) and didn't solve the valid STT fragmentation (Deepgram still finalized early). I've reverted to `0.5s` (and `0.2s` for barge-in) as `stop_secs=2.0s` is considered an anti-pattern for conversational flows. 3. **Prompt Engineering (Aggressive):** - I instructed the LLM to "call the function IMMEDIATELY with whatever fragments you have". - *Result:* This led to early failures where the LLM would call `capture_phone("6")`, which would fail validation (requires 9 digits), causing the bot to reject the input before the user finished speaking.

Guys, do you know how to use PersonaPlex from Nvidia with LiveKit or Vapi?

Built AI phone systems from scratch. Know the full stack—scoping, design, development, testing, deployment. Systems can handle inbound calls, appointments, CRM integration for service businesses. Ready to launch but need partners who can source clients. Split profits 50/50. You handle sales, I handle delivery. Interested? Let's talk.

Just spent 2 hours engaging with clinic owners on LinkedIn. Here's what I'm seeing: The gap between clinical excellence and patient reach is massive. Brilliant practitioners with 10+ years of experience are struggling with the operational side while their calendars have gaps. Three patterns keep showing up: 1. Premium clinics with beautiful websites losing 80% of calls to competitors who just rank higher on Google Maps 2. Technology that technically works but creates daily friction because it does not match how the clinic actually operates 3. Owners competing on price instead of outcomes, which erodes margins and authority The solution is not more marketing. It is operational excellence that lets quality practitioners focus on what they do best. When you never miss a call, follow up consistently, and remove booking friction, you stop competing on price and start competing on experience. 2026 is about depth over noise. Quality plus visibility working together. What operational gaps are you seeing in your market?