Voice AI

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

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.

It would be amazing to have the live voice chat agent be able to transfer the web call to a live person when asked. I have a customer on a 14 day trial right now. They have been testing the agent in multiple senarios and love the results so far. The one task they wish the agent could do is hand the call over to a live person if the visitor asks. It is not certain that they will continue after the 14 day trial but I know if the agent was able to successfully transfer to a human, it would almost certainly seal the deal. Please find a way! Thank you

Was excited to switch from Vapi to GoHighLevel Voice AI, but Outbound calls require a disclaimer upfront telling the lead they are an AI Assistant. WHY is that needed when we receive their opt-in consent to receive AI calls? A huge number of leads simply hang up when they hear 'AI Assistant.' Can we PLEASE make this optional like every other platform? It is basically useless to my many subaccounts now and we will stick with Vapi.

Add support for a custom word pronunciation dictionary that allows users to define how specific words (such as brand names) should be pronounced by the AI voice agent, similar to the functionality offered by HeyGen and ElevenLabs. Problem Statement: Currently, voice agents rely on default Text-to-Speech (TTS) pronunciation rules. This causes incorrect pronunciation of brand names, proprietary terms, and industry-specific words. For example, our brand name Soccerfy must be pronounced “Soc-ker–fye”, but TTS engines often pronounce it incorrectly (e.g., “Soc-ker-fee”). This leads to: Brand inconsistency Reduced professionalism Confusion for callers Poor customer experience There is currently no reliable way to enforce consistent pronunciation across all voice interactions. Proposed Solution: Introduce a Custom Pronunciation Dictionary that allows users to: Define a custom word or phrase Specify the correct pronunciation using: - Phonetic spelling (e.g., “Soc-ker-fye”) - IPA or SSML phoneme notation (optional) Apply the pronunciation globally across: - Voice agents - Call scripts - Dynamic AI responses This dictionary would override the default TTS behavior whenever the custom word appears. Example Use Case: Custom Word: Soccerfy Display Text: Soccerfy Pronunciation: soc-ker-fye Whenever the AI agent speaks “Soccerfy,” it should consistently pronounce it as “Soc-ker-fye” without requiring manual script changes or workarounds. Comparable Implementations: HeyGen: Custom pronunciation entries for brand and proper nouns ElevenLabs: Pronunciation dictionaries with phoneme-level control These platforms demonstrate that this feature is technically feasible and significantly improves voice consistency. Business Impact: Improves brand trust and professionalism Ensures consistent pronunciation across all AI agents Reduces manual scripting workarounds Enhances enterprise readiness for branded voice deployments Critical for agencies and businesses using AI voice at scale Suggested Priority: High — essential for production-grade voice agents and branded AI deployments. Optional Enhancements (Nice to Have): Per-agent pronunciation dictionaries Per-language pronunciation rules UI preview / test pronunciation button Bulk upload of custom words

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

It is very frustrating when making outbound ai calls that we can not choose weather we want the disclaimer to be played before the call or to at least edit what it says. Were paying a lot of money for this and to not have control of how we decide to use it is a communist way of doing business!

I have a client who would like his inbound AI employee to use his own voice so that his customer interactions are more personable. I would like to be able to upload an AI voice file that I've trained with external software, or be able to train the custom AI voice within GHL. Thank you for all you do for us! ie. https://elevenlabs.io/voice-cloning

Within the 'Voice AI Agent / Call Transfer Action,' it would be highly beneficial to enable transfers to extensions. Many businesses rely on existing phone systems where a single contact number connects to various team members using extensions. Currently, to forward calls to specific extensions, companies would need to purchase a separate DID for each extension, which is just another added cost. To improve this, the 'Phone Number to Transfer to' field could allow for extensions by supporting commonly used symbols to separate the main number and extension, such as a comma (pause), semicolon (wait), or pound/hash symbol (e.g., +61 1234-4567,123). Adding this functionality would enhance flexibility and compatibility, and it may only require updating the field to accept these symbols.