So, its been a long process and a lot of work - literally re-writing our voice orchestration to be native - and we still have a small sprint before we will start flowing traffic that way. Here is just a general guide of somethings that will change, be added and be deprecated. So, rollout. first - the users using our numbers will start seeing the traffic flow first. Then older numbers. Then trunked numbers. Nothing tangible changes from your perspective besides lower latency. Tooling - So, we are adding POST / GET / PUT / PATCH / DELETE to api request types. We also have it where you can configure headers, query parameters, path parameters and body parameters. So, fully customized API calls. We will suppose variables in these as well so you can pass API keys or your access token for GHL. Here's the thing, tools is now running through a proxy of ours that will open up the doors for a couple things: - Tools to run as they do today - Direct API calls (will be a toggle), so instead of being wrapped in a args object with metadata, etc - we will just send the API call. This gets rid of the need for middleware because you can make direct API calls. - Workflow execution; not today or the next week but we are adding native workflows to the platform. You can configure a custom tool to trigger a workflow locally to run multi-agent frameworks and basic automation so we will support a middleware internally. Abilities - all stays the same, but we are adding agent teams in voice (chat following right after). So, add different assistants into call to create a team env on the call either through a "prompt change" so we just change the prompt dynamically, or through a team so mutliple voices, etc. AI Models - We will be running a custom fine-tuned model thats been fine-tuned for voice orchestration. aka, this llm outputs text-to-speech friendly output to keep weird translations to a minimum. You will be able to select an OpenAI model if you would like and run it with your key if you prefer OpenAI output.

Hey everyone, I have a question about voice AI best practices. I’ve been experimenting a lot with voice AI, but I feel like some of you have absolutely mastered it. Your call recordings sound insanely human and incredibly fast. Meanwhile, when I try to replicate the same thing, I can never seem to reach that level. So I wanted to ask the community: What exact best practices are you using to make your AI calls sound both extremely fast and extremely human? Specifically, I’d love to hear about: 1. Which AI model you’re using — GPT-4.0, GPT-5, or something else 2. Whether voice quality mostly comes from the voice clone, the model, or the prompting 3. Any prompting structures, tricks, or settings that noticeably improve speed or realism 4. Any small details you’ve found that make a huge difference in conversational flow There isn’t any real documentation that explains what the “gold standard” setup looks like, and I feel like we could all benefit from sharing what has actually worked in the real world. I’ve tried talking to a few people one-on-one, but it feels like we don’t yet have a centralized place to compare notes. If you’ve dialed in a setup that works incredibly well, I’d really appreciate anything you’re willing to share. Thanks in advance! I think we can all learn a lot from each other on this.

I'm new here

Anyone else encountering this issue, my chat widget will work perfectly fine. It's setup to book an appointment/asks questions about their business once it asks for a number and I input a number into the widget it breaks The widget will only spit out this response "Sorry, I encountered an error. Please try again." I have to then completely remake the widget but I keep running into this issue Also is there a Discord server? Would be cool to screenshare with other builders to converse and get help more directly! Thank you

Hey sorry this is probably a really easy fix, but I can't seem to get this working. I'm trying to make an outbound call using a call_now tag in my agent. The tag is being added onto my contact in GHL but for some reason it won't initiate the outbound call. The agent itself says it's able to make outbound calls and that there are no errors on assistables. I bought and imported my own number from Twilio that didn't fix it. I can call the number and it'll initiate the call & work fine, just having problems with outbound. Also just upgraded to the $279 plan but that didn't fix anything either, Added screenshots for context. I feel silly please let me know what I'm missing