Voice AI

While Conversation AI via text can schedule appointments, Voice AI agents currently cannot. Without this feature, users are forced to turn to other platforms to fill the gap. It disrupts our workflows and diminishes the value of staying entirely within Go High Level. Adding this capability would keep people from needing another platform, Instead keeping everything in one place, making Go High Level "The" go to solution for seamless Voice AI scheduling. If you agree this should be a priority, please upvote this post to help get it on the developers' radar!

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.

Please provide the same "train with url" capability to the Voice AI agents. This will drastically improve performance. Thanks

We have a lot of numbers and it would be great if we could select multiple numbers so we don't have to set up multiple bots.

Allow additional knowledge base for voice ai agents via documents and external URLs.

I am looking for an AI to do cold calls and would be happy if there would be a possibility to test it for u too. like a beta

Enhance the responsiveness of the Voice AI Employee by incorporating natural-sounding verbal fillers (e.g., “uhmm,” “okay,” “uh-huh,” “so”) before delivering a full response. These subtle cues serve two purposes: Indicate to the user that the AI is actively listening. Provide a buffer period that reduces interruptions if the user continues speaking. Problem: Currently, the Voice AI Employee often responds either too early, cutting the user off mid-sentence, or too late, creating awkward silences that reduce the sense of real-time interaction. This breaks the illusion of human conversation and can frustrate callers. Proposed Solution: Introduce verbal fillers and soft interjections at strategic timing intervals. These can include: “Uh-huh…” “Okay…” “yea…” “So…” “uhmmm…” How it Works: As the user finishes or appears to finish a sentence, the AI first delivers a soft verbal filler while still monitoring for continued speech. If the user resumes talking, the AI pauses its main response. If no further input is detected within a short window (e.g., 0.5–1 second), the AI proceeds with the full, appropriate reply. Benefits: Improved User Experience: Conversations feel more human and less mechanical. Reduced Interruptions: Users don’t feel rushed or cut off by the AI. Increased Trust & Engagement: The verbal cues make the AI feel more like a thoughtful, attentive assistant. Adaptable Behavior: These fillers can be randomized and matched to context or tone, making them feel intentional and varied. Optional Enhancements: Customizable Voice Personality: Let users choose the type and frequency of fillers to match brand tone (e.g., casual vs. professional). Intelligent Pause Detection: Enhance pause detection accuracy with machine learning to anticipate if a user is likely to continue speaking. Why This Matters: Callers are more likely to engage, trust, and convert when they feel heard. A conversational AI that mirrors natural human speech patterns—especially in timing and tone—can dramatically improve call outcomes and user satisfaction.

I think the title explains it well enough. Adding Elevenlabs will open a wide range of voice and language possibilities.

I'm having a problem where the ai voice and the caller are always talking over each other, and the ai sometimes cuts off the caller. This needs to be cleaned up.

I have noticed that the voice agent is very sensitive, even the smallest background noises can throw it off and disrupt the conversation. Is there anything in the works to help the dsp not be so sensitive to picking up everything? This would be super helpful.