Hi Everyone, We are working to create a multilingual messaging system inside of GoHighLevel using Claude's MCP server. We are going to be programming it to rebill our clients using Stripe's subscription-based SAS billing. That way we can rebill the tokens and API calls to Claude. That'll be the billing model at cost per message. Has anyone built that before? Specifically, I want to make sure it's safe and doesn't delete any data. I only want it to send messages and emails for right now, and the messages will be on all the regular social media channels via GoHighLevel: - SMS - Web chat through a chat bubble - Whatsapp - Email We're currently programming the voice function of this inside Retell. We're curious about using our building our own AI at some point to rebuild it and then having the same billing model with the MCP server and Stripe with Syncs billing model. My overall questions are: 1. What's a good way to set this up to make sure all the data is secure, as we cannot delete any client data? 2. What are good ways to pressure test all of this? 3. Has anyone here built anything like this before? 4. Where is a good starting point with getting this all set up? 5. What are good ways to set up the initial prompt and knowledge base for all this? This will be for filtering leads for immigration lawyers, so we're going to need to put quite a bit of information in. However, we don't want the bot to give legal advice or guidance.

This video is a hands-on walkthrough of Retell AI's brand new Conductor feature, which lets you use AI to build, test, and configure your AI voice agents directly inside the platform. See how to generate full agent prompts, create function calls, run simulation test cases, and adjust settings like response eagerness and interruption sensitivity, all through natural language. If you've been using Claude Code to hit Retell APIs, Conductor replaces that workflow natively. Check it out 👇👇

Hi everyone. What's everyone using to do natural-sounding speech inside of VoiceAI? Right now, we're using Retell with 11 Labs to have that. The voice doesn't sound bad, however, the speaking cadence is a little off, so we're wondering how to prompt and program all the AI and have a good knowledge base to where it speaks at more of a natural flow. How is everyone tackling this?

Hi everyone. We're building a personalized outreach intake system for processing immigration leads, meaning an immigration law firm will hire us, use the system to qualify and screen their leads, and help them sign up cases. We're looking at ways to have a natural-sounding voice. We're currently using Retell that we have with Twilio as the primary phone system, and then behind that we were looking at using Eleven Labs to have more natural-sounding voice than the voice provided by Retell. Currently, the process of this is to have it all synced Go High Level to schedule paid and unpaid appointments for people and do post consult follow up. How have people found more natural-sounding voices with AI so it doesn't sound like AI itself?