# Vapi Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/vapi
> Markdown URL: https://aitinkerers.org/technologies/vapi.md
> Technology record last updated: 2026-03-02T14:44:02Z
> Generated: 2026-09-22T14:47:24Z

Vapi is the API platform for deploying advanced, human-like voice AI agents with sub-600ms latency across phone, web, and custom applications.

Vapi is the core developer platform for building and scaling voice AI agents, handling complex infrastructure so you focus on the experience. The system orchestrates three core technologies (Speech-to-Text, LLM, Text-to-Speech) to enable real-time, natural conversations: achieving sub-600ms response times for human-like turn-taking. Agents offer full phone integration (inbound/outbound calls) and web embedding, plus Tool Calling to connect to your existing APIs for complex workflows (e.g., appointment scheduling, data retrieval). This is a modular, enterprise-grade solution designed for reliability and scale.

- Official technology site: https://vapi.ai
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [A2A: Two Agents, One Job](https://sf.aitinkerers.org/talks/rsvp_lglB83xwkc4)

I’ll demo a live agent-to-agent workflow between Holly, an AI recruiter, and Hunter, an AI career agent. Holly works for hiring companies and posts jobs into an ATS; Hunter represents candidates, helps them apply, and negotiates on their behalf. The demo will show how both agents connect through structured events and tool calls (e.g., send_email, vet_candidate, schedule_interview), autonomously coordinating the hiring flow from job posting to candidate introduction.

- Event context: Protocol Demo Night at WorkOS (MCP, A2A, AG-UI) — 2025-10-10 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_lglB83xwkc4

### [Dynamic AI Voice Agents with VAPI](https://la.aitinkerers.org/talks/rsvp_DaFGliLt3-U)

VAPI AI is a popular voice agent framework, but is limited when you want to change your AI agents in response to user inputs. I have discovered some clever tricks to overcome these limitations and make more advanced agents.

- Event context: Feb 24 - LA AI Tinkerers Meetup & Demo — 2025-02-25 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_DaFGliLt3-U

## Related Technologies

- [Go](https://aitinkerers.org/technologies/go) ([Markdown](https://aitinkerers.org/technologies/go.md)) — 25 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Unipile](https://aitinkerers.org/technologies/unipile) ([Markdown](https://aitinkerers.org/technologies/unipile.md)) — 2 public demos