Skip to Content
FeaturesConversational AiConversational AI Overview

Conversational AI Overview

Voxvaani’s Conversational AI features enable intelligent, automated conversations across voice and chat channels using AI-powered agents and chatbots. The Chatbot uses Gemini only (gemini-3.1-flash-lite, hardcoded). Voice AI Agents support both OpenAI and Gemini providers, configured in Organization Settings.

AI Agents vs Chatbot

CapabilityAI Agents (Voice)Chatbot (Text)
ChannelPhone calls (integrated into IVR flows)Text-based (WhatsApp, web chat)
InteractionReal-time voice conversation with text-to-speech outputAsynchronous or real-time text messaging
Primary Use CasesCustomer support hotlines, lead qualification calls, FAQ automation, appointment schedulingCustomer inquiries, lead capture, support ticket creation, FAQ responses
Flow ControlAdded as a node in IVR Flow Builder; can transfer to human agentsHandles the full conversation or escalates to a human agent

When to Use AI Agents

  • You receive a high volume of repetitive phone inquiries
  • You need 24/7 phone support without staffing night shifts
  • You want to qualify leads by phone before routing to a sales team
  • You have an IVR menu and want to replace rigid key-press options with natural conversation

When to Use Chatbot

  • Your customers prefer text-based communication (WhatsApp, web chat)
  • You need to capture leads from inbound messages automatically
  • You want to reduce support ticket volume by answering FAQ autonomously
  • You are running WhatsApp campaigns and need to handle responses

Quick Start

  1. Choose your AI provider — Voice AI Agents support OpenAI or Google Gemini based on your language requirements, pricing preferences, and response quality needs. The Chatbot uses Gemini only.
  2. Configure your API key — Add your provider’s API key in Settings . A Gemini API key is required for the Chatbot; voice agents require the key for your chosen provider.
  3. Create your first Agent or Bot:
    • For voice: Navigate to AI Agents, define a system prompt, select your model, and add the agent as a node in your IVR Flow Builder.
    • For text: Set up a Chatbot, configure its prompt and behavior, then connect it to your WhatsApp or web chat channel.
⚠️

API Key Costs. Each conversation turn consumes API credits from your chosen provider (OpenAI or Gemini). These costs are separate from your Voxvaani plan. Monitor your API usage through your provider’s dashboard to avoid unexpected charges. Estimate your monthly cost by multiplying your expected conversation volume by the average tokens per interaction.

How It Works

Detailed Flow

  1. Input Reception — A call reaches an AI Agent node in the IVR, or a message arrives at the Chatbot
  2. Context Loading — The system loads the configured system prompt, conversation history, and contact context
  3. LLM Processing — The message or transcribed speech is sent to the configured AI model (OpenAI or Gemini for voice agents; Gemini only for chatbot) along with the system prompt
  4. Intent Recognition — The model determines the user’s intent (e.g., “check balance”, “speak to agent”, “create ticket”)
  5. Action Execution — Based on intent, the system either:
    • Generates a text/speech response
    • Creates a support ticket
    • Captures and saves lead data
    • Transfers to a human agent or fallback node
  6. Response Delivery — For voice: TTS is played to the caller. For chat: text response is sent back.
⚠️

API Key Required. The Chatbot requires a Google Gemini API key configured in Settings . Voice AI Agents require either an OpenAI or Gemini API key. Without a configured API key, these features will not function. Each API call consumes credits from your chosen provider.

Requirements

  • OpenAI API Key or Gemini API Key configured in Settings  (Gemini required for chatbot; voice agents support either)
  • Properly configured AI Agent or Chatbot settings
ChatbotEmail Campaigns