Voice AI

Best

Feature Request: Please extend the existing DTMF (keypad button press) capability — currently only available through the "transfer_call" action — so it can also be used as a standalone action during outbound calls, allowing the AI Voice Agent to navigate automated phone menus (IVRs) when calling businesses. Use Case: When doing outbound B2B calling — for example, calling a business's main line — the call almost always hits an automated IVR system first ("Press 1 for Sales, Press 2 for Support," etc.) before reaching a live person. GHL's Voice AI Agent already has DTMF functionality built for the transfer_call action, but it isn't available earlier in the call flow. Since the agent has no way to press digits before that point, it gets stuck at the IVR and can't get through to a live rep. Right now every call that hits an IVR just stalls or drops. What's needed: Ability for the AI agent to detect/listen for IVR prompts and either: Automatically press a pre-configured digit sequence at a defined point in the call, or Dynamically decide which digit to press based on the IVR prompt it hears (ideal), or At minimum, decouple the existing "press digit" tool from transfer_call so it can be added as its own standalone action the agent can trigger mid-call, any time during an outbound call Why this matters: This is already a standard, supported feature with every major AI voice platform — Vapi, ElevenLabs (Conversational AI), and Retell AI all support DTMF/keypad press actions as an independent tool available throughout the call, not gated behind a transfer action. GHL already has the underlying DTMF capability built — it's just tied to transfer_call — so this is a real blocker for anyone trying to use it for serious outbound B2B calling where reaching a live rep through a phone tree is the norm, not the exception. Adding this would bring GHL's voice agent to full feature parity with the other platforms and unlock a huge use case (outbound dialing to businesses) that's currently not viable with the current setup.

Would be extremely helpful to keep the same point of contact.

Security needs to for the company and housing

It would be most valuable for the AI to be able to assign a caller to a user and book the appointment under the caller's preferred user/staff member. For example, if someone is calling because they want to book with a particular staff member/user, that appointment should end up in that user's column. Right now, that feature is available through the booking widget and through the calendar page, but the Voice AI is booking appointments and assigning them at random even after being told "preferred team member/staff member" and the Voice AI repeating back and confirming "preferred team member/staff member".

The first sentence the Voice AI speaks usually determines whether or not the caller will know it's AI and hang up, or feel comfortable continuing the conversation. While it is currently a feature to use your own voice for AI receptionists, they don't sound great if used for the entire conversation. Thus it'd be great to be able to personally record just the welcome message so that it sounds human, then the rest of the conversation is carried on by the AI voice. It will encourage callers to state the reason that they're calling before hanging up, so that the AI agent can at least be given the chance to respond to their needs.

The Ask Tradies are on the tools all day and can't always answer their phone. They want: During work hours — if a call isn't picked up (they're on a job, on a roof, hands full), the Voice AI steps in as a backup so the call isn't lost. After hours — once the work day ends, the Voice AI automatically takes every call, without the tradie's phone ringing at all.

Problem When an existing contact calls a Voice AI agent, the agent has no idea who is calling. It greets everyone generically and follows the same intake flow (name, email, callback number) even though the caller's phone number already matches a contact in the sub-account. The call is correctly attached to the contact card afterwards, so the match exists; it just isn't available to the agent during the call. Result: existing customers get asked for their name and email again, refuse ("you already have my details"), and the call feels like a form instead of support. In our logs this is the number-one source of friction. Requested feature Before the agent's opening line, perform a contact lookup on the inbound caller ID and expose the result to the agent as variables, for example: {{contact.found}} (true/false) {{contact.first_name}}, {{contact.last_name}} {{ contact.email }} {{ contact.company }} {{contact.tags}} or a "customer status" field {{contact.last_activity}} The agent prompt can then branch: "Hi {{contact.first_name}}, welcome back" for known contacts and skip the name/email steps; full intake for unknown numbers. Why the current options don't cover it WORKFLOW_TRIGGER runs asynchronously and cannot return data into the live call. KNOWLEDGE_BASE is static content, not live contact data. A custom webhook function in Retell works technically, but it sits outside GHL, requires the API key per sub-account, and is not something an agency can roll out or maintain across dozens of client sub-accounts. Suggested scope Automatic lookup on inbound caller ID, matching on E.164 phone, same logic already used to attach the call to the contact card. Selected contact fields injected as prompt variables (configurable per agent, so agencies control what the agent may see). Optional: expose the same lookup as a mid-call action ("look up contact by phone/email") for callers who withhold their number. Business impact Shorter calls, fewer abandoned intakes, and existing customers treated as existing customers. For agencies this is the difference between a demo feature and a receptionist clients will actually keep on the line.

We are unable to offer service to our Telugu clients based out of Telangana and Andhra Pradesh because Voice AI doesn't support Telugu language natively. Could you able to provide Telugu language support also asap.