When it comes to scaling voice AI, concurrency matters more than setup. From testing, I’ve noticed a difference between Retell and Vapi: Retell can handle around 20 concurrent calls• Vapi is closer to 10 concurrent calls in most setups But this isn’t just about the platform. Your actual limit still depends on: • API rate limits (LLM + voice) • latency• backend setup So, while the tools provide a baseline, real scaling comes from how well your system is optimized. Most people hit infrastructure limits before platform limits. What kind of concurrency are you actually hitting with Vapi or Retell right now?

Getting WhatsApp Business API approval is the hard part. Meta requires business verification, template approval, and messaging limits before you can scale. One thing that helped me was using platforms that simplify the setup and handle the infrastructure layer. Tools like 2Chat or Whatsscale make connecting automation workflows much easier. Curious how others here are handling WhatsApp automation.Are you using the official API or another platform?

One day, the thing you’re struggling to finish will inspire someone else to start. Create, inspire!