Voice AI

In voice ai agent, when a caller mentions a phrase I want to transfer the call to a cell phone. If that caller doesn’t pickup, I want to transfer it to a different cell phone. I know the primary transfer can be done within the agent with an action, but the secondary transfer is not currently possible.

With companies like Nedzo that have ultra realistic voices, I think the HL voice ai has a long way to go. Would be good if the voices could sound less robotic.

The AI Voice Agent could experience spam phone calls. Could there be a way to block incoming numbers - I see this as being a problem with my GHL (business number). This could disrupt Automation and Workflow with bad information and fake contacts.

Voice AI needs a true warm-transfer option that gives the receiving person context and control before the caller is connected. For example, imagine an attorney’s office using Voice AI as its receptionist. A caller contacts the firm about a new legal matter. Voice AI gathers the caller’s name, reason for calling, type of case, urgency, and other relevant information. If the call should be escalated to an attorney or intake specialist, the system should be able to contact that person privately first. The receiving person could hear something like: “You have John Smith calling about a potential personal injury case from an accident that occurred yesterday. He is not currently represented. Press 1 to accept this call or press 2 to decline.” If accepted, the caller is connected. If declined or unanswered, Voice AI should return to the caller and continue the configured fallback experience, such as taking a message, collecting additional information, scheduling a consultation, or letting the caller know someone will follow up. Ideally, the private whisper could dynamically include information gathered during the AI conversation, such as: Caller name Reason for calling Type of inquiry Urgency Qualification information Short AI-generated summary This would be valuable across many industries, including legal, medical, insurance, home services, property management, sales teams, and professional offices. Without an accept/decline step, answering the transferred call immediately connects the human to the caller. That limits Voice AI’s ability to function as a true receptionist or gatekeeper. A true warm transfer would allow Voice AI to screen the call, gather context, brief the human privately, and then hand off the conversation only when appropriate. That would make Voice AI significantly more useful for businesses that want AI to protect their team’s time while still providing a high-quality experience for important callers.

As we work towards offering AI receptionists to clients, it would be super helpful if the AI could train based on previous call transcripts. For example if we have someone call in and ask to speak with Patty, the AI may not realize they're asking for Patricia. Or maybe industry jargon is used on calls, it would be helpful if the AI can learn what all those terms are so it can respond properly. Some of this stuff only turns up in client calls, and in an ideal scenario, after the call the AI would ask the sub account owner or admin to clarify or add context to what was discussed on the call.

We can currently send an email transcript after the call is completed, but it would be nice to actually send the recording and summary with it too

This would be great for 2 reasons. 1) When one of your contacts is calling using the AI phone number they would be recognized " Hi John" Thanks for calling, how can I help you? 2) When doing voicemail drops to sell AI voice the caller could call back, be recognized and have a demo of what their missing on their call back.

An ability to test or demonstrate the Voice AI by just clicking a widget or a button in a funnel/website.

Currently, Voice AI uses structured prompts and logic to handle live phone conversations and guide callers through different questions and scenarios. My recommendation is to extend that same conversational framework into website forms, allowing a form itself to function as a chat window rather than a static set of input fields. ⸻ Conversational Form Window The idea is to embed a chat-style interface directly inside a form, using the same prompts, training, and agent goals that power Voice AI or Conversation AI. • Instead of a floating chat widget, users could interact with the AI directly within the form section of the page. • The AI would guide visitors through questions in a natural, message-based format, collecting the same information as a phone call — but through text. This would make forms feel interactive and human while maintaining the same conversational flow and data capture logic that already exists within the Voice AI system. ⸻ Benefits • Seamless user experience: Visitors stay on the page and interact within the form without pop-ups or distractions. • Professional appearance: The chat interface becomes part of the page design, matching brand aesthetics rather than relying on a floating icon. • Consistent data collection: The same prompts and workflows used in Voice AI can be mirrored here, ensuring uniform lead qualification across phone and web. • Higher engagement: Visitors who don’t want to speak on the phone can still complete a guided, conversational intake through the website. ⸻ This would give GoHighLevel users a way to create conversational, AI-powered forms that feel personalized and dynamic — not just another chatbot floating on the screen. It also keeps the logic unified across Voice AI, Conversation AI, and now interactive web forms. Thank you for considering this — it could be a major step forward in how businesses collect leads and communicate through AI on their websites.