Voice AI

Let Voice AI agents join meeting room meetings — with an avatar face, video, and recording
Please let Voice AI agents join meeting room meetings — the built-in meeting rooms in KontactKeeper — so we can have conversations that are not just limited to phone calls. Right now, Voice AI agents can only work over the phone. There is no way to bring one into a meeting room, schedule it into an interview, or have it meet a client or team member face to face on video. What I want: Schedule a Voice AI agent into a meeting room meeting, the same way I would invite a person. The agent joins with an avatar face the other person can see — or voice only, if we prefer. The person on the call can turn on their video, and we can record the meeting. How this helps communication with clients and the team: a phone call is one channel; a meeting is another. Interviews, onboarding conversations, and team check-ins happen on video because seeing a face builds trust in a way a voice alone does not. An agent that can sit in the room — visible, listening, asking questions — can hold a real conversation instead of a phone script. Who benefits — everyone who meets people inside HighLevel: Agencies scheduling interviews with clients or team members: the agent runs the interview, asks the questions, and records it. Coaches and course creators: an agent that can join a coaching call or a student onboarding meeting. Sales teams: an agent that joins a discovery call on video, with a face, and records what was said. Multi-location businesses: one agent that can meet each location's team in their own meeting room. Churches and ministries: an agent that can join a pastoral or volunteer meeting and take notes. Any team that records meetings: the conversation is captured in the meeting room, not lost after a phone call. Why it benefits HighLevel: meeting rooms are already built into the platform — this makes them the place where AI conversations happen, not just human ones. It turns Voice AI from a phone feature into a meeting feature, which gives every agency a reason to run more meetings inside HighLevel instead of on Zoom or Google Meet, and every recorded agent meeting is more content, more notes, and more follow-up work that lives in the CRM.
0
Transcribe audio and video files in Media Storage, and offer a cheaper transcription option for phone calls
I run an agency and I am building a system that turns my clients' audio and video into content — but right now HighLevel cannot transcribe a file that already sits in Media Storage. I have to send my clients out to third-party tools like AssemblyAI, which breaks the workflow and sends them (and their data) off the platform. What I am asking for: Transcribe audio and video files already in Media Storage. Let me select a file, get an accurate transcript, and use it — turn a video into a blog post, social clips, show notes, captions, or a follow-up email — without leaving HighLevel. Include a preview/mockup of the transcript output so I can show a client what the service delivers before they buy it. Let agencies offer transcription as a service we resell at a slight markup, the way AI usage is billed today. I want to provide transcription to my clients as part of my packages. Give us a cheaper transcription option for LeadConnector phone calls. The current phone transcription price is quite high. A powerful, reliable, lower-cost provider such as AssemblyAI would save every agency money on the calls we already record and transcribe. Why this helps everyone: every agency records calls and hosts videos. Transcripts turn those recordings into searchable content and faster follow-up instead of dead files. Coaches, speakers, churches, home-services and real-estate teams all have hours of audio and video sitting unused — transcription turns it into marketing that brings in business. For HighLevel, transcription becomes a new usage-based revenue stream that agencies willingly resell, and a cheaper phone-transcription option means more agencies actually turn transcription on instead of leaving it off over price. Keeping transcription in-platform also keeps client data inside HighLevel instead of flowing out to third-party tools.
0
BYOK - bring our own keys
#### Overview As GoHighLevel continues to evolve its AI capabilities—particularly with Agent Voice for conversational automation—there's a clear opportunity to empower users with greater control over their LLM providers. Currently, the built-in model options are solid but limited, which can constrain innovation, cost management, and compliance needs. Implementing Bring Your Own Key (BYOK) natively would allow users to integrate custom API keys from any LLM provider (e.g., OpenAI, Anthropic, Grok/xAI, or others) directly into Agent Voice workflows. This feature should support configuration at both the agency level (for centralized management) and sub-account level (for client-specific customizations). #### Key Benefits Enhanced Flexibility: Users could leverage the latest or most cost-effective models without waiting for GHL to onboard new providers. For instance, switching to a specialized voice-optimized model like Grok's voice mode or a fine-tuned local setup could dramatically improve conversation quality and latency. Cost Optimization: Agencies and businesses could route traffic to the most economical providers based on usage patterns, reducing reliance on a single vendor's pricing. Privacy & Compliance: BYOK enables self-hosted or on-premise LLMs, ensuring sensitive data stays within your infrastructure—critical for industries like finance, healthcare, or legal. Future-Proofing: With the LLM landscape exploding (new models weekly), this keeps GHL at the forefront without constant backend updates. #### Proposed Implementation Configuration Options: - Agency-Level: Global settings in the agency dashboard for shared keys/models across all sub-accounts, with override permissions. - Sub-Account-Level: Per-client toggles in the sub-account settings for tailored integrations. - Fallback Mechanism: Default to GHL's native models if a custom key fails or isn't configured. Supported Integrations: - API Key Upload: Simple key entry fields with validation (e.g., test prompt on save). - Local/SSH Models: Option to connect via SSH to self-hosted instances (e.g., Ollama, Llama.cpp) for zero-cloud dependency. Include secure tunneling and authentication guides. - Provider Presets: Pre-built templates for popular APIs (OpenAI, Anthropic, Cohere, etc.) to streamline setup. Agent Voice Enhancements: - Model selection dropdown in voice workflow builders, pulling from BYOK configs. - Real-time monitoring: Usage stats, error logging, and A/B testing between models. - Voice-Specific Tweaks: Parameters for latency tuning, accent adaptation, or interruption handling per provider. #### Why This Matters Now The current model selection is a great starting point, but it doesn't match the pace of AI innovation. Without BYOK, users are locked into a narrow ecosystem, forcing workarounds like external Zapier integrations or custom code—which add complexity and cost. This feature would position GHL as the most developer-friendly CRM on the market, attracting power users and agencies who demand sovereignty over their tech stack. I've seen similar implementations in tools like LangChain or Vercel AI SDK drive massive adoption; GHL could lead the charge in no-code AI.
0
Load More
→