Voice AI

Our team manages multiple clients within similar industries, where approximately 90% of the knowledge base content is identical, with only minor variations between accounts. Currently, there is no efficient way to reuse this content. Each time we onboard a new client, we have to manually recreate or copy and paste the knowledge base from scratch, which is time-consuming and increases the risk of inconsistencies or errors. Proposed Solution: Introduce the ability to clone or duplicate an existing knowledge base into another subaccount. Ideally, this would allow us to: Select an existing knowledge base as a template Clone it directly into a different subaccount Make minor edits as needed without rebuilding from scratch Impact: Significantly reduces onboarding time for new clients Ensures consistency across similar accounts Minimizes manual work and human error Improves scalability for agencies managing multiple clients

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.

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.

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

We already have a caller on the line, why does the bot need to transfer them to another phone number so another bot can take over?

We specialize in helping homeowners sell properties across the U.S., regardless of location. One issue we’ve identified is that our AI outbound system relies on phone number area codes to determine timezone, which is not always accurate. Many clients retain phone numbers from previous states, causing the system to misidentify their timezone. For example, a client living in Arizona with a Maryland area code was contacted at 5:00 AM local time because the system assumed they were in Maryland. This resulted in a poor client experience and a lost lead. To resolve this, all outbound calls should be scheduled strictly based on our business timezone, not the client’s assumed timezone. This ensures that calls are only made during our defined business hours, regardless of the lead’s phone number origin. By standardizing calls to our office hours, we eliminate inconsistencies caused by inaccurate timezone detection and maintain a predictable, professional outreach process. Until this issue is resolved, AI outbound calls present a risk to client experience and brand reputation. We need to address this immediately to continue using GHL effectively.

Recently I tried to develop a workflow in my voice AI agent to enable appointment rescheduling. Sometimes it works, sometimes not. I think you can enable the Appointment rescheduling function for voice AI agents, it helps lots to me and others to develop proper workflows

Outbound Voice API that allows us to trigger outbound campaigns to smart lists. Allowing for throttling, agent selection, calls per day, hours of operation, and all the goodies that Outbound Voice has but through V2 Oauth API. In my perfect world - You would set a campaign name, Select your target Audience (smart list), Select your AI Agent, Write a campaign goal/prompt, select caller Id number (verified Id), set max dials per day, set operating hours, and maybe have a 'voicemail' strategy like does it hang up and try again or does it drop a pre-recorded voicemail.. I'll take some version of this lol.. Please tell me this is coming soon!!

Voice AI needs a built in realism engine that reviews calls and tells agencies why the agent still sounds robotic. Not more basic settings. We need call scoring and automatic improvement suggestions based on real conversations. Needed MVP: Score every call for human realism Detect awkward pauses Detect talking over the caller Detect robotic phrasing Detect repeated phrases Detect rushed responses Detect slow response latency Detect missed interruptions Detect when the agent asks too many questions at once Detect when the caller sounds confused or frustrated Show exactly where the call felt unnatural Suggest prompt fixes automatically Suggest greeting fixes automatically Suggest knowledge base fixes automatically Suggest voice and pacing changes automatically Allow one click apply to agent settings Let agencies compare two versions of the same agent Add a test mode with caller personas like angry customer, price shopper, emergency caller, elderly caller, bad audio caller, and fast talker The goal is simple. Do not just give us knobs to adjust. Tell us why the AI sounds fake and help us fix it faster. Details Voice AI needs a built in realism engine that reviews calls and tells agencies why the agent still sounds robotic. Not more basic settings. We need call scoring and automatic improvement suggestions based on real conversations. Needed MVP: Score every call for human realism Detect awkward pauses Detect talking over the caller Detect robotic phrasing Detect repeated phrases Detect rushed responses Detect slow response latency Detect missed interruptions Detect when the agent asks too many questions at once Detect when the caller sounds confused or frustrated Show exactly where the call felt unnatural Suggest prompt fixes automatically Suggest greeting fixes automatically Suggest knowledge base fixes automatically Suggest voice and pacing changes automatically Allow one click apply to agent settings Let agencies compare two versions of the same agent Add a test mode with caller personas like angry customer, price shopper, emergency caller, elderly caller, bad audio caller, and fast talker The goal is simple. Do not just give us knobs to adjust. Tell us why the AI sounds fake and help us fix it faster.

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.