Urgent.News

What's breaking now, across thousands of outlets.

AI

how to build voice ai for inbound calls

You can have a Vapi agent answer every inbound call, ask qualifying questions, and hand the prospect off to Calendly to lock in a meeting - all without writing a single line of custom telephony code. The result is a self-contained voice AI agent that routes calls, captures lead data, and books calendar slots automatically. voice is the audible sound produced by a human speaker that can be…

Building a voice AI agent for inbound calls can be achieved without writing any custom telephony code. This solution involves using Vapi, Twilio, Calendly, and n8n to create a self-contained voice AI that routes calls, captures lead data, and books calendar slots automatically.

To begin, you'll need a Twilio phone number and a Vapi agent. Set up a Twilio number by buying a local US number in the Twilio Console. Configure the number to forward calls to an n8n webhook once the call is connected.

Next, create a Vapi agent using its JSON payload. This agent will ask the caller for their name, company, and a brief description of their challenge. Once the conversation is complete, the agent will forward the captured data to n8n via a webhook.

Twilio will then forward the call audio to the Vapi agent. The agent will run the qualification script, and once it's done, it will send the lead data to n8n. The n8n workflow will then enrich the lead information and create a Calendly event for a scheduled meeting.

In summary, to build voice AI for inbound calls, you'll need a Twilio phone number, a Vapi agent to handle the conversation, an n8n workflow for lead data processing and calendar booking, and optionally, a HubSpot CRM to store qualified leads. The entire process can be completed in 1-2 days, assuming you already have accounts for all the required services.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

The best free AI models 2026 for an automation-first business

The best free AI models 2026 are the ones that give you production-grade quality without a bill at the end of the month. In practice that means using Groq's ultra-low-latency mix, Google Gemini's 1…

  • Groq's Mixtral-8x7B-instruct offers low-latency text generation for free AI models in 2026.
  • Google Gemini 1.5 Flash provides 1M input/output token free quota for businesses.
  • Meta's self-hostable LLaMA 2 13B model and DeepSeek's open-source v2.5 offer 150k free tokens.

The best argument against my MCP server came from Anthropic

Building in public You know the risk before you start. Everyone tells you: do not build something the platform could ship. You build it anyway, because you need it and nobody has it.

  • Anthropic's memory feature in Claude Code rendered the author's MCP server redundant.
  • Author built a memory layer for AI coding assistants to improve subsequent tasks.
  • Author's memory server outperformed Anthropic's memory in recall consistency tests.

How to Review AI-Generated SQL Before You Trust the Number

An AI assistant will write you a query in ten seconds, the query will run, and the number that comes back will look completely reasonable.

  • Count rows before trusting sum to detect fan-out causing double-counting
  • Look for NULL values in filter conditions to avoid improper exclusion
  • Place filters in WHERE clause before HAVING clause for accurate calculations

More from Saturday 22 August →