Multi-provider voice AI showcase featuring 7 providers (ElevenLabs + Widget, OpenAI, xAI, Ultravox, Vapi, Retell, Google Gemini Live) with real-time transcripts, audio visualization, and glassmorphism UI. Built with React 19 + TypeScript.
# Voice-Agent-PuPuPlatter > **Project assembled by [AI with Apex](https://AIwithApex.com)** ## [VIDEO] Video Tutorial Series Learn how to create and configure ElevenLabs agents (in general and) for this application: | Tutorial | Description | | ----------------------------------------------------------------------------------------------- | ------------------------------------------------------------------ | | [DOCS] [Building Your First ElevenLabs Agent](https://youtu.be/oEkyNSWRqxc?si=30fMIpIhm0hgbzfz) | Complete walkthrough of creating your base conversational AI agent | | [FILES] [Setting Up Knowledge Base (RAG)](https://youtu.be/S93uZ9Cuz4w?si=WxEtWKrEzx_e5XBL) | Quick 60-second guide to prepare your agent's knowledge base | | [TOOLS] [Creating Agent Tools & Functions](https://youtu.be/jHTMYmptHI0?si=1O0kVsWjTDr6bbVC) | Build your first agent tool for contact detail collection | | [NOTES] [Handling Call Transcripts](https://youtu.be/--j6hfnCc-w?si=Hz12v8ukPi4y2pU4) | Process and manage post-call transcripts effectively | | [NEW] [Advanced Features & Configuration](https://youtu.be/55UJWHi_ZMk?si=p58wnk-bmEkgDg2_) | Explore new features and advanced usage patterns | --- A sophisticated multi-provider voice AI web application built with React 19, TypeScript, and support for 8 different voice AI providers. Experience real-time voice conversations with beautiful audio visualizations and a modern glassmorphism UI. ## Built With - The very first version featured just the Elevenlabs Widget and was built with Lovable.dev and Gemini - All revisions to the app since its initial launch were made with Claude Code Plugin Skill 'Apex Spec System': https://github.com/moshehbenavraham/apex-spec-system ## [FEATURES] Features ### Core Features - **Real-time Vo
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.