I've been testing VAPI for a pizzeria voice assistant and experiencing critical random performance issues with zero configuration changes: Problems: Transcription: Perfect on some calls, catastrophic on others (empty/missing words)Voice quality: 3 different voice IDs in a single call, random number pronunciation (French/English mix)Latency: 1-2s on some calls, 4-7s on others (same config)Behavior: Repeated question loops (asked 5x in a row), lost context, excessive API callsContext: Use case: French phone assistant for order takingInvestment: Dozens of hours testing/configuringStatus: Cannot deploy to production due to unpredictabilityRequest to VAPI: Need technical explanation within 48h: Why performance varies without config changes?What parameters affect stability?Is there a fix?If no valid solution → requesting full credit refund. Cannot build client services on an unpredictable platform. Anyone else experiencing this? Any workarounds?

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team

I’m running into the same core issue: performance is highly inconsistent with no configuration changes, which makes the platform unreliable for production. On some calls everything works perfectly, and on others transcription breaks, voices switch, latency spikes, and the assistant loses context. This usually points to backend routing and model switching rather than anything in our setup. Without the ability to lock providers and models, it’s impossible to guarantee stable customer experience. Can you confirm whether calls are being routed across different STT/TTS/LLM providers or regions during execution? @willasss66

This is serious issue for production, I can help u to resolve the issues so that you can better serve. Let me know

@willasss66 have you checked that your org is on the 'Weekly Channel' in organization settings.? If no config changes/degradations then this would have an impact https://cdn.discordapp.com/attachments/1469786991649362052/1469848432419279051/image.png?ex=69892686&is=6987d506&hm=cf6efe18e4e98368224587ffadcaef4be92b00363411611c9050eae257e5d5c6&

sorry for the trouble. could you please share the call ids of the calls where these issues occurred?

t es qui toi?