Hack #7: v0

Audible has over a million audiobooks and world-class narrators. But their website makes you feel nothing. No atmosphere, no emotion, no way to discover what to listen to based on how you actually feel right now. This redesign started with one question — what if the website actually matched the product? The problems I identified: Discovery is broken. Audible asks you what genre you want. But nobody thinks in genres. They think in feelings. I'm stressed. I can't sleep. I want to escape. So I replaced genre dropdowns with 8 emotional states. You tell it where you are, it finds what you need. Book pages tell you nothing personal. They show you a price and a runtime. They don't tell you if this book is right for you, right now. So I added an AI that has actually read the book. You ask it anything — it answers out loud. The website is completely silent. This is a product sold entirely on the power of voice and narration. So every interaction that matters — recommendations, book answers, genre teasers — speaks back to you through ElevenLabs. Voice in, voice out. Tech Stack: — Google Stitch for visual design direction — v0 by Vercel for UI build — Claude for architecture and design decisions — Groq for real-time AI responses — ElevenLabs for all voice output

LINKEDIN OS 👁️ A dystopian corporate operating system powered by AI. Everyone talks about AI replacing jobs. But what happens when AI starts deciding your value? So I redesigned LinkedIn as the corporate surveillance platform of the future. 🟥 Real-time employability scoring 🧠 AI recruiter monitoring 📈 Promotion probability analytics 🎙️ Voice-powered HR assistant using ElevenLabs ⚡ Reimagined in v0 “The future of work has been optimized.”

Hacker News(https://news.ycombinator.com/) is the thinking layer of Silicon Valley. Every day, engineers, founders, and researchers gather on a single page to figure out what matters first. It surfaces the ideas shaping the industry before Twitter, newsletters, or the mainstream catches up. But the interface hasn’t changed since 2007. HN++ is a full redesign of Hacker News. The content and product stay the same, but the design is completely reinvented. The experience is rebuilt from scratch with glassmorphism, warm SF-inspired tones, frosted cards, and a calmer reading flow without losing information density. Three modes shape the product. Highlights surfaces the best stories of the day by topic. Feed is the live firehose of everything happening on HN in real time. Podcast turns the front page into something you can listen to, with a built-in player and daily episodes generated automatically from top stories. Everything streams live from the official Hacker News Firebase API. The audio experience adds a completely new dimension to HN. Every story includes a Listen button that generates a short narration blending the article with the comment discussion. HN++ Pod is a fully automated daily podcast built from the day’s top threads. Voice Search lets you query HN by speaking naturally. HN++ Bot is a conversational agent with live access to Hacker News — ask what’s trending, what people are debating, or who’s hiring. Built with ElevenLabs (Text-to-Speech, Scribe v2, Text-to-Dialogue (Eleven v3), ElevenAgents, Music API), Vercel v0 for component generation and easy deployment, Firecrawl for scraping, Gemini as the intelligence layer, Cloudflare R2 for storage, and GitHub Actions for daily podcast automation. Hacker News has always had the best content on the internet. HN++ gives it a surface worthy of it — and now a voice. HN++: Same firehose, new senses!

AmazonAI is a fully voice-controlled e-commerce platform built for the ElevenLabs x v0 Hackathon that revolutionizes online shopping through conversational AI. Users can browse products, apply filters, add items to cart, and complete checkout entirely through natural voice commands eliminating the need for clicking, typing, or navigating complex menus. This hands-free approach makes shopping accessible for everyone, whether they're cooking, driving, or have accessibility needs. Core Features Voice-Powered Product Discovery: Users can say "Show me dresses under $50" or "Only red ones with free shipping" and the AI agent instantly applies filters and displays matching products. The agent understands natural language preferences for price, color, brand, category, and shipping options in real-time. Context-Aware Shopping: When viewing a product detail page, users simply say "Add this to cart" and the agent recognizes the current product without requiring a product name. The system automatically navigates to the cart and confirms the action. Conversational Checkout Flow: The agent guides users step-by-step through checkout. Users provide delivery details conversationally ("My name is John Smith", "Email is [john@gmail.com](mailto:john@gmail.com)", "Address is 45 Park Street, Mumbai") and the form fills automatically without manual input. Smart Navigation: Voice commands like "View my cart", "Go back to shopping", "Proceed to checkout", and "Place my order" allow seamless navigation throughout the shopping journey. Real-Time Feedback: A debug panel tracks all voice tool calls, errors, and agent responses in real-time, helping users understand what the agent is processing. User Journey User connects the voice agent on the Shop page. User speaks natural language commands like "Show me keyboards under 100 dollars with free delivery". Agent applies filters and displays results. User browses products and says "Tell me about the wireless keyboard". Agent navigates to product details and reads specifications. User says "Add this to my cart". Agent adds item and navigates to cart page. User reviews order summary and says "Proceed to checkout". Agent navigates to checkout form and asks "What's your full name?". User provides details conversationally, agent fills form fields automatically. User says "Pay by cash on delivery" and agent selects payment method. User says "Place my order". Agent confirms and displays order confirmation. Key Benefits Accessibility: Hands-free shopping for people with mobility challenges, visual impairments, or situational limitations. Speed: Voice commands are faster than traditional clicking and typing for browsing and checkout. Convenience: Users can shop while multitasking, driving, cooking, or with hands full. Natural Interaction: Conversational AI understands colloquial language and context, not rigid command structures. Error Resilience: Smart fallbacks for ambiguous voice input, multiple product matches, and network issues. AmazonAI demonstrates how conversational AI can transform e-commerce into an inclusive, accessible, and frictionless experience. it proves that voice-powered shopping isn't just a nice-to-have feature but a fundamental reimagining of how people interact with online stores.

I redesigned a local fried chicken spot's website because they deserved the revamp and their chicken is soooo good! Vercel's v0 surprisingly made it super simple to redesign the website and used way less tokens than I expected. Elevenlabs was used to create all of the demo audio which made putting together a presentation a breeze.

Wikipedia — Neubrutalist Edition What I Built A live Wikipedia client with a bold Neubrutalist UI and AI-powered Text-to-Speech. Every article, image, and news feed is fetched in real-time from en.wikipedia.org. Users can search, browse trending articles, explore categories, and — most importantly — highlight any text to hear it read aloud by an AI voice. What Problem It Solves Wikipedia's interface is stuck in the 2000s and has no native audio feature. This project gives it a modern, visually striking redesign while adding voice accessibility — so anyone can listen to articles instead of reading them. How ElevenLabs Is Used ElevenLabs powers the listen feature. When a user selects text, it's sent to a secure Next.js API route that proxies the request to ElevenLabs' eleven_turbo_v2_5 model. The generated MP3 streams back to the browser for instant playback with play/pause controls and download. The API key stays server-side for security, and input is capped at 2,500 characters to manage costs. How v0 Is Used v0 by Vercel was used to design and build the entire frontend — the Neubrutalist design system (thick borders, hard shadows, zero radius, vibrant colors), all page layouts (homepage, articles, search, categories), the component library, responsive design, and dark mode. It turned what would be days of CSS and layout work into rapid, iterative prototyping.

spotify.trm - A terminalcore redesign of Spotify with an AI radio DJ. I cloned Spotify's product shape (library, search, queue, player) in v0 and reimagined every pixel as a terminal: monospace fonts, green-on-black palette, command logs, splash gate, and a real CLI tab where you can type play weeknd, queue lofi, or dj on and it just works. Same mental model people already know — re-skinned for keyboard-first users. Then I added a voice layer with ElevenLabs. The app has four AI DJ hosts — Nova, Velvet, Pulse, Kai — each mapped to a distinct ElevenLabs voiceId plus a per-host delivery string for v3-style acting control. When a track is about to end, Groq's llama-3.1-8b-instant reads the next track's metadata and writes a one-line intro in that host's persona. ElevenLabs speaks it server-side via /api/tts. The next iTunes preview starts quietly under the voice-over so handoffs feel like a real broadcast instead of dead air. Same queue, different host, completely different vibe. Stack: Next.js 16, React 19, Tailwind 4, v0, Groq, ElevenLabs, Vercel. Code: github.com/anirxdh/spotify-for-hackers

I redesigned the NASA Space Place website, https://spaceplace.nasa.gov/, which teaches elementary kids about astronomy. I recreated all the original content while giving it a beautiful, kid-friendly UI. Not only that, but I also introduced a new way of learning. Instead of the traditional reading experience, the website leverages the ElevenLabs API to guide students through lessons with engaging narrations, animations, and fun interactive activities. I used this week’s sponsor, v0, to clone the existing content and redesign it with an amazing UI, and I used the ElevenLabs API to generate kid-friendly narration.

Listing is a modern reimagining of Craigslist built for the age of AI. The project explores a simple idea: what if classifieds actually evolved? Built with v0, Listing transforms the traditional static classifieds experience into a cinematic, voice-first marketplace that feels alive, interactive, and intelligent. Users can search naturally using voice, compare listings with AI-generated trust and pricing analysis, discover local events, and even create listings entirely through conversation. Using ElevenLabs, voice is deeply integrated into the experience through conversational search, spoken AI comparison verdicts, and voice-powered posting workflows that make buying and selling feel effortless and modern. Inspired by nostalgic internet culture and futuristic product design, Listing blends the familiarity of local classifieds with the intelligence and usability expected from today’s AI-powered experiences.

I integrated ElevenLabs (STT) for hands-free queries, v3 (TTS) for real-time GugleLabs narration, and the Conversational AI SDK to allow users to interrupt and talk to the 3D data nodes.(yet, before pushing last update to add the widget, v0 left out of credits.) What makes it special? The project features a "Synesthesia Engine", a procedural Web Audio layer where the 3D environment physically pulses and morphs its geometry in real-time response to the Agent vocal frequency and sentiment, and further navigation with voice assistance. Google/v0/Elevenlabs P.S did this in the memory of google search engine R.I.P since we slowly shift towards agentic use. lol

reimagined the @vercel dashboard as a terminal. no UI. no buttons. just: → monospace everything → keyboard shortcuts (⌘1-3) → char scramble hover effects → pixel art mascot that boots on load and Rabbit — an @ElevenLabs voice agent named after Evil Rabbit say "what's broken" and he tells you. two sentences. no filler. built for the v0 × ElevenLabs hackathon ↓

We completely redesigned the official FIFA World Cup 2026 Hospitality website (https://fifaworldcup26.hospitality.fifa.com/us/en) as a dark, cinematic, editorial experience and added something the original doesn't have: a voice concierge powered by ElevenLabs that lets you talk to the website. The Problem: The 2026 World Cup is the most complex in history. Three host countries, 16 venues, 104 matches, 48 teams. Navigating this information through traditional filters and tables is overwhelming, especially for fans planning cross-border trips. Our Solution: A voice-first AI concierge that knows every match, venue, hospitality package, and team schedule. Ask "Where does Argentina play?" and it answers instantly, then navigates you there. Ask "What matches are in Mexico City between June 14-18?" and it cross-references everything for you. The agent doesn't just answer. It acts on the UI: scrolling to sections, navigating between pages, and highlighting relevant content. Design: We replaced the corporate light theme with a layered dark luxury aesthetic. Radial glows, pitch blueprint SVG overlays, animated ball trajectory paths, glassmorphism panels, 3D Three.js hero scene, editorial section numbering, and a tri-accent color system (Cyan / Gold / Pitch Green). Every section feels like a premium sports magazine. ElevenLabs Integration: The Conversational AI SDK powers a persistent floating voice dock across all pages. We feed the full tournament data (104 matches, 48 teams, 16 venues, pricing) into a RAG knowledge base. The agent uses client-side tool calling to navigate the site, making voice a first-class interaction method, not a gimmick. Built with: v0, Next.js 16, React 19, Three.js, Tailwind CSS v4, ElevenLabs Conversational AI SDK

CribSwipe takes Craigslist, the most aggressively ugly apartment listing site on the internet, and reimagines it as a Tinder-style swipe experience for NYC apartment hunting. Craigslist hasn't meaningfully changed its UI since the 90s. Blue links, dense text, no images on the index, a layout that punishes you for wanting somewhere to live. CribSwipe keeps the exact same content (NYC apartment listings) and rebuilds the entire interaction model from scratch. The redesign: The text-wall index becomes a full-bleed swipe deck: photos, price, neighborhood, key amenities at a glance Filtering happens through voice conversation instead of dropdowns and checkboxes The whole UI was built in v0 The audio layer: Meet Vinny, a fast-talking virtual realtor powered by ElevenLabs Conversational AI. Tell Vinny what you want ("two bedroom under 4k in Brooklyn, no walkups, dogs okay") and he filters the deck for you. He has opinions. He will roast your budget. He sounds like he's been showing apartments in Bay Ridge since 1994. The conversation drives the filters. The filters drive the deck. You swipe right on the place, not the realtor. Stack: v0 for the full UI rebuild ElevenLabs Conversational AI for Vinny using multiple real-time tools, context updates, and prompt overrides. Static Craigslist listings (live scraping would violate their TOS, but a real version would pull live data) Try it: cribswipe.com

**ElevenLabs Terminalcore Redesign** transforms the modern, clean ElevenLabs website into an immersive 1980s hacker aesthetic featuring green phosphor text, CRT scanlines, ASCII art, and glitch effects. The redesign preserves all original content and products while completely reimagining the visual style as an authentic terminal interface with command-line interactions. Full ElevenLabs API integration enables real-time text-to-speech generation with multiple voices, waveform visualization, and an interactive Voice Narrator that guides users through the site with audio narration. The site features animated boot sequences, typewriter effects, matrix rain backgrounds, and terminal-styled components that create an immersive, engaging experience. This project demonstrates how v0's AI-powered design capabilities combined with ElevenLabs' voice AI can create a distinctive, memorable redesign suitable for viral marketing and hackathon submission.

**ElevenLabs.io Reimagined** is a bold Neubrutalism redesign of the ElevenLabs landing page that transforms the original glassmorphic aesthetic into a high-contrast, visually striking experience with cream backgrounds, thick black borders, and vibrant flat colors. The site deeply integrates the ElevenLabs text-to-speech API as a core interaction model—every section has a "Listen" button generating audio narration, and an interactive playground lets users select voices and hear custom text generated in real-time with live waveform visualization. The blog section dynamically pulls content using the Firecrawl scraping API, ensuring data accuracy and demonstrating multi-API integration. A persistent global audio player with streaming support and client-side caching provides seamless audio playback across all sections. The project showcases how voice AI can be woven into the entire user experience—not as an afterthought, but as the foundation of interaction design.

# Brutalist Voice AI A brutalist redesign of ElevenLabs with integrated text-to-speech audio overviews. Raw industrial aesthetic (black/white, thick borders, monospace type) meets AI voice technology. Click any section to hear AI-generated narration powered by ElevenLabs TTS API. Built with Next.js, Tailwind, and Framer Motion. **Why it matters:** Proves AI voice tech doesn't need glossy UI—sometimes raw authenticity is more powerful. Accessible, fast, and hackathon-ready.

I reimagined Wikipedia with a minimalist, reader-first experience focused on clarity, learning, and immersion. The platform combines clean editorial design, intelligent search, AI-powered word definitions, synced text-to-speech, and customizable reading controls to make exploring knowledge feel modern and effortless.

V0X11HACKS is a retro analog horror experience player styled as a CRT monitor with VHS aesthetic. It streams disturbing found-footage narratives with synchronized ElevenLabs v3 voice narration, atmospheric images, and subtitles. Each story is accompanied by glitchy transitions, scanline overlays, chromatic aberration effects, and authentic VHS degradation filters to create an immersive creepy viewing experience reminiscent of 1980s-90s tape media.

I redesigned the ElevenLabs website to look like a 6 year old drew it with crayons. Same product, completely different vibe. Built in v0 with wobbly borders, Crayola colors, doodle decorations and Permanent Marker font throughout. The ElevenLabs integration is a crayon mascot called Echo who lives on the site. Ask it anything via voice, it transcribes using Speech to Text, responds in a childlike TTS voice, and can even transform your voice to sound like him using Speech to Speech. Every page section also has a hover triggered TTS narration where Echo describes it like a kindergartener.

I cloned the Natural History Museum London homepage using v0, then completely rebuilt it as a cinematic scroll experience — where a T-Rex guides you through iconic exhibitions. v0 generated the entire React codebase and UI system, while ElevenLabs powered the atmosphere: ambient soundscapes created with ElevenLabs Sound Effects, and a narrator voice (Emilia) telling the Dino's day at the museum through ElevenLabs Text to Speech.

**Linear.app Brutalist Redesign** transforms the sleek, minimal project management tool into a raw, intentionally jarring aesthetic powered by pure brutalism. The design features thick black borders, zero border radius, neon lime accents, monospace typography, and high-contrast layouts that flip Linear's polished brand into something viscerally different. The site includes an animated hero section, feature cards with brutalist styling, interactive pricing tiers, and auto-rotating testimonials—all maintaining Linear's original messaging and content. ElevenLabs text-to-speech integration adds voice narration that automatically plays section descriptions as users scroll, with manual replay controls and visual status indicators. This is a high-impact design transformation perfect for showcasing how a single product can radically shift aesthetics while keeping functionality identical—ideal for the hackathon's "Redesign the Web" challenge.

**Project Overview** This is a Linear.app-inspired project management platform built for a hackathon, featuring a distinctive Terminalcore + Glassmorphism hybrid aesthetic — combining dark terminal-inspired backgrounds with frosted glass panels and neon accent colors. The app includes core task management features like issue tracking with list and kanban views, project tracking with roadmap timelines, and team collaboration tools with workload visualization. The standout differentiator is ElevenLabs voice AI integration, offering voice-guided onboarding tours, daily standup audio summaries, comment narration, and ambient sound effects for task completion. An AI Overview feature provides context-aware voice explanations of each page's design and functionality, helping users and judges quickly understand the interface. The project is fully responsive, keyboard-first, and production-ready with comprehensive documentation.

NASA · Transmit is an editorial cinematic redesign of nasa.gov. Every word stays verbatim from the live site — every headline, every Artemis II crew name, every mission. The rendering is reimagined as a magazine you fall into. Same content. Different ceremony. Three ElevenLabs integrations: ↳ Pre-generated voice tour (TTS API) ↳ Composed ambient soundtrack (Music API, 2:30 instrumental) ↳ Conversational AI agent — Mission Control voice that answers live questions about the ISS Built and scaffolded with v0. Vite, vanilla JS, no framework, no design library. 16kb before first paint. Signature moments: a hard contrast flip from cosmic dark to warm cream paper with an embossed wax seal. A horizontal scroll-jack from low Earth orbit to Voyager 1 with a tension drone rising in pitch. A cursor flashlight section revealing hidden constellations. The constraint of "you cannot change a single word" was the most generative brief I've worked from. Live: nasa-eight-smoky.vercel.app

We used v0 to give the open-source cheat sheet QuickRef.ME a complete visual redesign, transforming the traditional cold, hard document list into a developer knowledge note wall with a "kraft paper + handwritten notes + stamp" style, making the tedious task of looking up commands and reading syntax feel like flipping through a notebook for taking notes. Technically, we used v0 to generate and iterate all React components and the Tailwind visual system (card rotation, paper texture, tape and pins, hover lift, detail page expansion animation, bilingual i18n switching, recent browsing history, and site-wide search) from scratch. We also used v0 to seamlessly integrate the Next.js 16 / React 19 project structure. ElevenLabs was responsible for "bringing the paper to life"—using the Sound Generation API (/v1/sound-generation) to generate paper sound effects such as page turning and tearing in real time based on prompts, and using the Text-to-Speech API (eleven_multilingual_v2 multilingual model + Rachel voice) to allow the note assistant in the lower right corner to read commands aloud in both Chinese and English. Combined with browser voice input, this creates a natural language query loop of "say a sentence, search for a command, and listen to it read it to you." What makes it special is that it is a "skin-changing" re-creation of a tool site (quickref.me) that global developers use every day—using generative AI to repackage the most familiar and rational content of engineers into a warm, tactile, and even sound physical desktop experience, proving that v0 + ElevenLabs can upgrade a plain text tool site into a multimodal product with emotional memory points.

**ElevenLabs Y2K Edition** is a nostalgic redesign of ElevenLabs.io that reimagines cutting-edge AI voice technology through the lens of late 90s/early 2000s web design. Built for the ElevenHack Hackathon, it features an authentic Windows 98 interface with neon colors, pixel fonts, and CRT scanline effects, while delivering real functionality via OpenRouter for text generation and ElevenLabs API for text-to-speech conversion. The centerpiece is an interactive "VOICE_LAB.exe" demo where users type a prompt, receive AI-generated responses, and instantly hear them played through a retro WinAmp-style audio player. Beyond the visual experience, the project includes a voice-guided tour (TOUR.exe), keyboard sound effects, and a retro loading screen—all while maintaining full accessibility support with skip links, focus states, and reduced-motion preferences. It's a playful demonstration that combines nostalgic design with modern AI capabilities, proving that the future sounded better from 1999.

SafeSpace is X (Twitter) reimagined as a wellness app for emotional toddlers. Same product — feeds, profiles, replies, blocks — completely reinvented as a kindergarten-coded sanctuary where you argue with AI replicas of anyone via voice, then they "set a boundary" and disappear into your Healing tab. Forever. _________________________________ What we built SafeSpace is a parody redesign of X (Twitter) as a wellness app. Same content layer — feeds, replies, profiles, the right-column trends, the blocking mechanic — completely reimagined visually and tonally. Where X is dark blue and combative, SafeSpace is sage and pastel and Comic Sans. Every word of UI chrome ("Healing tab," "feelings going around today," "people who hurt others like you") translates platform mechanics into wellness-cult language. The redesign isn't decorative. It's the joke. The aesthetic and the microcopy reveal what the platform's mechanics already encourage: blocking framed as "setting a boundary," timelines framed as "your truth," confrontation framed as something to be filtered out. What it does Type any X handle. SafeSpace generates an AI replica of that person — personality, posting voice, tweet corpus — using the Claude API. ElevenLabs Voice Design generates a unique voice from a personality description. Within 30 seconds, the user is in a session with a fully argument-capable replica of @elonmusk, @joerogan, or anyone else. The argument loop is voice-driven. The user speaks; the browser transcribes; Claude refines the venom into a postable tweet; the user releases it; the replica generates a reply (in character, escalating as the user pushes harder); ElevenLabs streams back the audio in the replica's generated voice. Victoria, the wellness facilitator, narrates the experience. A pastel "patience meter" rings the replica's avatar and drains as venom accumulates. When the user pushes too far, the replica blocks them. The conversation freezes, gets archived in the Healing tab forever, and Victoria congratulates the user. "@elonmusk needs some quiet time. you're so brave." _________________________ How it uses ElevenLabs Voice Design generates a unique voice for each dynamically built replica from a personality description. The same architecture pre-bakes voices for the six built-in replicas. TTS streaming delivers replica replies in real time during arguments. Pre-generated narration for Victoria's onboarding tour, where she introduces the user to their safe space across five visual beats. _____________________ How it uses v0 v0 generated the initial scaffold — the Twitter-style three-column layout, the modal compose flow, the right-column suggestions, the action bars, the trending section. From there, the visual reinvention was applied: pastel palette, Comic Sans, cloud-shaped cards with hand-drawn lumpy borders, marshmallow buttons, soft cloud-pattern wallpaper. Same product, completely different visual world. What makes it special SafeSpace works at two layers simultaneously. As a redesign, it's a clean reinterpretation of X's UI in an unexpected visual style — exactly what the brief asks for. As a piece of art, it's a comment on what the platform already is: a tool for cataloging the people who've made you feel small, dressed up as connection. Every replica you build is fully voice-capable. The dynamic build flow is real engineering — Claude generating personality + corpus, ElevenLabs Voice Design generating a matching voice, retry logic for transient API errors, in-session escalation that hardens the replica's tone as the patience meter drains. The whole pipeline runs in under 30 seconds per replica. The real product fits the fake one perfectly. The wellness-cult skin makes the architecture make sense. ________________________ Tech stack / built with v0 by Vercel Next.js 16 Claude API (claude-haiku-4-5) ElevenLabs TTS ElevenLabs Voice Design Tailwind v4 TypeScript Web Speech API localStorage

I redesigned the official openAI website and integrated a text to speech section, a voice command to navigate to certain sections, An a tour guide on the website

ElevenGov: A Satirical EU Government Portal Powered by ElevenLabs TTS What I Built: A Next.js web application that reimagines ElevenLabs' cutting-edge voice AI technology as a deliberately bureaucratic 2016 European Union government portal. The project combines real AI-powered text-to-speech with satirical design to create an entertaining yet fully functional demo. Problem It Solves: While showcasing advanced technology is important, making it approachable and memorable is equally crucial. ElevenGov demonstrates how satire can make complex AI technology more engaging and shareable, turning a technical demo into an experience people want to talk about. How It Uses ElevenLabs: - Real-time TTS generation via ElevenLabs API (eleven_multilingual_v2 model) - Server-side proxy pattern for secure API key management - "Dirk" - a deterministic chatbot assistant whose responses are narrated using ElevenLabs voices - Page narration feature that reads official "government documentation" aloud - Audio panel with live waveform visualization during speech generation Technical Implementation: - Next.js 16 App Router with TypeScript - Secure /api/tts endpoint proxying ElevenLabs API - Custom bureaucratic UI components (shadcn/ui) - Keyword-based assistant with TTS playback - Complete architecture documentation with Mermaid diagrams The Comedy Factor: Every modern web design trend is deliberately reversed - grey backgrounds, Arial font, 1px borders, rectangular buttons, and fake EU directives like "Form PBV-2024" and "Directive 2024/VOICE/47". It's AI-powered voice technology presented in the most boring way possible, which somehow makes it hilarious.

AI Race Engineer is an immersive Formula 1 strategy intelligence platform that transforms race data into cinematic, real-time tactical analysis. Redesigned using v0, the platform reimagines how fans experience race strategy through predictive analytics, dynamic visual storytelling, and voice-driven race engineering. Users can compare any two drivers during a race simulation and instantly receive AI-generated insights including undercut and overcut probabilities, projected pit windows, tyre degradation trends, and tactical race reasoning. Instead of presenting this through a conventional dashboard, the redesign focuses on recreating the atmosphere of a real Formula 1 pit wall using animated driver presentations, cinematic transitions, tactical overlays, and responsive AI strategy panels. And to top it all, the experience integrates ElevenLabs voice AI and sound effects to generate streamed race engineer commentary immediately after each analysis completes. Users do not just read the strategy — they hear realistic engineer-style communications delivered in real time, making the experience feel like live pit wall interaction during a race session. AI Race Engineer explores how generative UI and voice AI can transform complex Formula 1 strategy decisions into an interactive, cinematic, and emotionally engaging experience.

Duolingo landing page in a Soviet Constructivist Propaganda aesthetic — the complete opposite of Duolingo's friendly, rounded, playful brand. Same product. Same content. Completely opposite design. Blood red, near-black, and aged cream replace the cheerful greens. Anton condensed type replaces the rounded friendly fonts. Zero rounded corners anywhere. Every illustration regenerated in a flat woodcut style. The friendly owl is now a stern commissar pointing directly at you. "Free. Fun. Effective." becomes "Free. Relentless. Effective." Built completely in v0 by Vercel. Audio narration generated and powered by ElevenLabs — a single authoritarian voiceover plays from the hero section, delivering the full page as a state mandate. One button. One voice. No friendliness.

I built a tactical AI sales agent for a DTC energy brand using ElevenLabs Conversational AI as an always-on voice SDR embedded into a v0-built landing page — so visitors can ask anything about the product and get real-time, objection-handling answers instead of bouncing off static copy. It solves the core DTC problem: 97% of landing page traffic leaves without converting because pages can't hold a conversation.

**HackForge** is a Linear.app-inspired project management platform that merges Terminalcore aesthetics (dark backgrounds, monospace fonts, terminal-green accents) with Glassmorphism design principles (frosted glass panels, translucent UI, backdrop blur). The application features a dual-experience: a cinematic landing page with hero section and feature showcase, plus a fully-functional dashboard with project tracking, task management, team collaboration, activity feeds, and cycle progress monitoring. All three ElevenLabs integrations are live—a voice-guided tour narrates site sections via Text-to-Speech, a conversational AI chatbot answers questions with Web Speech input, and synthesized terminal sound effects (keystrokes, beeps, whooshes) reinforce the hacker aesthetic. Built with Next.js, Tailwind CSS v4 semantic tokens, and Framer Motion animations, the interface delivers a premium, cutting-edge experience optimized for presentation. The entire codebase prioritizes responsive design, visual clarity, and accessibility, making it production-ready for the hackathon event.

I redesigned the classic Winamp website with a futuristic Glassmorphism aesthetic without writing a single line of code. The original winamp.com has an outdated design that doesn't reflect the legendary status of the product. I reimagined it as a modern, premium music experience. How I built it: → Used Claude to plan the design concept and structure → Used v0 by Vercel to generate the full React UI with Glassmorphism style (frosted glass, neon glows, dark background, gradient text) → Integrated ElevenLabs Text-to-Speech API to add an AI voice narrator that introduces each section of the site — making it feel like a living, breathing music product What makes it special: The site doesn't just look alive — it sounds alive. ElevenLabs gives every section a voice, turning a static landing page into an interactive audio experience. Zero code written. Just prompts, creativity, and the right tools.

This project is a complete visual redesign of Stripe's payment platform website, transformed from its modern minimal aesthetic into a Y2K Cyber-Futurism style featuring chrome metallic text, holographic gradients, neon glow effects, cyber grid backgrounds, and CRT scan line overlays. Built with Next.js 16, React 19, and Tailwind CSS v4, the application consists of 12 custom React components including a hero section, features grid, animated statistics, interactive code editor, globe visualization, testimonials, and footer. The project integrates ElevenLabs text-to-speech API through a dedicated endpoint (`/api/text-to-speech`) that powers three voice features: a 5-step guided tour, an AI-powered feature overview with narration, and an audio showcase section demonstrating the voice capabilities. All original Stripe content and messaging is preserved while the visual presentation is completely reinvented with early 2000s cyber-futuristic design elements like floating 3D orbs, glassmorphism navigation, and animated holographic backgrounds. The project is production-ready, fully responsive, and designed specifically for the Vercel x ElevenLabs hackathon challenge to "Redesign the Web."

Intercom Terminal is a terminalcore redesign of Intercom as an interactive AI Support OS. I reimagined the traditional helpdesk website as a live command-center experience where customer conversations become logs, Fin runs like an agent daemon, tickets become queues, and support leaders can operate the workspace through terminal commands. Users can run commands like /scan, /fin, /tickets, /qa, and /briefing to inspect support metrics, Fin AI Agent activity, SLA-risk tickets, quality signals, and support operations summaries. The experience includes command autocomplete, a command palette, live-style support logs, dashboard panels, ticket routing views, Copilot draft previews, QA insights, command sound effects, and a responsive terminal UI. The problem it explores is that modern support teams often have too much information spread across dashboards, inboxes, tickets, reports, and AI agent logs. Intercom Terminal turns that complexity into an operational interface where important signals like SLA risk, topic spikes, sentiment changes, and AI resolution rates are easier to scan and act on. I used v0 to rapidly prototype and iterate on the full website redesign, transforming Intercom’s product structure into a completely different terminal-native visual and interaction system. I used ElevenLabs to create the audio layer of the experience. I designed a custom support-ops voice and generated a spoken manager briefing using ElevenLabs Text to Speech. When the user runs /briefing, the site plays an ElevenLabs-generated support summary covering message volume, Fin resolution rate, SLA-risk tickets, billing topic spikes, Copilot drafts, and recommended actions. The result is a playful but practical vision of what customer support could feel like in the AI Agent era: faster, more operational, more ambient, and easier to understand at a glance. Video - https://www.youtube.com/watch?v=VkC-m-jUOcI demo - https://intercom-clone-omega.vercel.app/

Stage is a Product Hunt-style arena where every product gets a voice — literally. When visitors open a listing, they can have a real-time Shark Tank conversation with the product itself: ask tough questions, hear the founder's pitch spoken aloud, and even talk back using their microphone. #How it works: * ElevenLabs powers both sides of the voice experience: * Text-to-Speech — Each AI-generated founder reply streams through ElevenLabs' API, giving every product a distinct voice that matches its chosen tone (e.g., "Confident · Direct" or "Warm · Approachable"). * Speech-to-Text — When users tap the mic, their audio is recorded via `MediaRecorder`, sent to ElevenLabs Scribe, and transcribed into a question the founder can answer. * Replicate (GPT-5 Nano) generates the founder replies. A detailed system prompt grounds the AI in the product's description, tagline, metrics, and private "Pitch Instructions" from the lister — so it stays in character and highlights what matters most. - v0 was used to design and build the entire full-stack app: database schema on Neon, file uploads on Vercel Blob, authentication, the pitch conversation UI, and this very submit form.

“V4 deployment in progress…” I transformed the ElevenLabs website into a cinematic short film documenting the launch of its latest voice model... Just press play.

I built a Neubrutalist reimagination of the brand Sticker Mule. It is the same product, but a huge improvement on the overall design. I built it using v0 to re-design it and included all seven product lines: stickers, labels, magnets, buttons, packaging, apparel, and acrylics. Tech Stack: ElevenLabs TTS streams through a custom `/api/tts` Next.js route with LRU blob caching. v0 generated every component. Web Audio API produces four in-browser SFX. No audio files needed. What makes it special: Voice is the navigation layer. Hovering any product card narrates it. Every review and case study has a "Play" button. The site works equally well with eyes closed.

Recreated the FIFA World Cup website into a "Football Gambling Room". "Situation Room" is a live, voice-driven prediction-market dashboard for the FIFA 2026 World Cup, built on Polymarket's Gamma API for real-time odds. ElevenLabs TTS gives it a bilingual football commentator that narrates goals and odds movements, and ElevenLabs Scribe (STT) powers a push-to-talk co-pilot for placing bets and asking for tips hands-free."

What if books on Goodreads can be summarized by an AI agent?

https://www.youtube.com/watch?v=59D7wbcGWYc - video Redesigning the San Diego Zoo website with ElevenLabs offers a chance to transform a static informational site into an immersive, "living" auditory ecosystem. By leveraging ElevenLabs’ low-latency streaming and expressive voice cloning, you can turn a browser window into a sensory gateway to the wild. I focused on three pillars: Atmospheric Immersion, Personalized AI Guides, and Multilingual Accessibility. 1. The "Wild Whisper" Ambient Hero Header Instead of just a video loop, the hero section becomes a generative soundscape. The Tech: Use ElevenLabs’ Sound Effects API (or integrated audio generation) to blend realistic animal calls with a soothing AI-generated narrator. The Experience: As users hover over different regions of a stylized park map (e.g., Panda Ridge or Africa Rocks), the background audio shifts. If they hover over the Pandas, a gentle voice narrates real-time "Panda Facts" in a tone that mimics a peaceful forest. Dynamic Lighting/Audio: The voice and background sounds change based on the user's local time. At night, the site adopts "Dark Mode" with the sounds of nocturnal animals and a hushed, whispered AI narration. 2. "Adopt-a-Voice" Interactive Wildlife Guides Move away from standard chatbots. Give every major animal exhibit a unique "Voice." The Tech: Use ElevenLabs Voice Design to create distinct "personalities" for different animals. Rex the Lion: A deep, gravelly, authoritative voice. Pip the Penguin: A high-pitched, energetic, and fast-talking voice. The UI: Each animal page features a "Talk to [Animal Name]" button. Users can ask questions about their diet or conservation status. The API Implementation: Use the ElevenLabs Conversational AI (Agents). Integrate it with a Large Language Model (LLM) like Gemini to process the zoo's database, then stream the response through the ElevenLabs API so the animal "talks back" with human-like emotion and inflection. 3. Real-Time "Live Cam" Narration The San Diego Zoo is famous for its live cams. Let’s make them accessible and engaging for people who can't watch closely. The Concept: An "Audio-Only Mode" for the live cams. The Tech: Use an AI vision model to analyze the live feed (detecting activity, like a tiger waking up) and send a text description to the ElevenLabs WebSocket for instant, low-latency speech synthesis. The Result: A user working at their desk can listen to a "Radio Wildlife" broadcast that says, "You’re listening to the Tiger Cam. Right now, the Malayan tiger is pacing near the watering hole—it looks like it’s getting ready for a midday drink." 4. The "Global Conservationist" (Instant Dubbing) San Diego Zoo is a global hub for conservation. The website should reflect that by breaking language barriers instantly. The Tech: Use ElevenLabs AI Dubbing API. The Feature: When the zoo posts a new video interview with a conservationist in the field, the website offers a "Listen in your language" toggle. The Impact: Instead of subtitles, the video is dubbed in real-time into 30+ languages, retaining the original speaker’s emotional tone. This makes the zoo’s mission accessible to a kid in Brazil or a researcher in Japan as if the speaker were native to them. 5. Sensory-First UI: Audio-Guided Navigation For an ultra-modern, accessible feel, implement a "Eyes-Free" navigation mode. Haptic & Audio Cues: When a user scrolls past a section, a short, expressive AI voiceover provides a 3-second "vibe check" of what’s in that section. Personalized Tickets: When a user buys a ticket, they receive an "Audio Ticket" narrated by their favorite animal voice, giving them personalized tips for their visit (e.g., "Hey there! I'm Omo the Hippo. Make sure you visit me before 10:00 AM; that's when I'm most active!").

I reimagined the website InterlinearBooks.com (featuring "subtitles for books": original stories in various languages for language learners with English translations) into Interlinear Cinema, a cinematic reading experience that enhances texts through AI-generated audio, sound effects and images to make them feel more engaging. It uses v0 to shape the interface into a theatrical reading experience with images and effects, and ElevenLabs to power narration, ambience, and sound cues that sync with the text. The result is a attempt to blend story, cinema, and AI-driven audio design: literature becomes something you don’t just read, but watch and hear unfold.

SpotifY2K: A nostalgic, retro-themed music application inspired by early 2000s hacker aesthetics. Experience what Spotify might have looked like if it were designed in 2001 by hackers.

Workday Neo: a reimagined HR platform where employees can talk to their HR system instead of clicking through it. Ask about your PTO balance, submit time off, check your 401(k) match, or navigate the app, all with your voice. HR portals are notoriously frustrating. Employees waste hours hunting through menus to find their vacation days or update their W-4. Workday Voice lets you just talk, like talking to a coworker who's read every policy doc and knows your paycheck by heart. - Vercel hosts the static site with instant deploys and edge performance - ElevenLabs Conversational AI powers the voice assistant: real-time speech recognition, natural language understanding, and human-like voice responses. The agent has full context of the employee's data (PTO, salary, benefits, schedule) and can execute actions like submitting time off requests or updating 401(k) contributions via client tools.

What if the USCIS website felt less like a government maze… and more like a clear map? For the Eleven Hacks challenge, I used v0 to inspire, clone, and rapidly recreate the USCIS website in a completely new visual style. I focused on one simple idea: people visiting immigration websites are often stressed, so the design should help them move forward faster. Key improvements: 1. Case status front and center 2. Common tasks grouped clearly 3. Cleaner visual hierarchy 4. Less searching, less stress 5. Official, but more human v0 helped me move from idea to working redesign much faster — turning inspiration into a full website experience instead of just a static mockup. A better government website should not just provide information — it should guide people when they need help the most.

I built GitHub Guild, a complete visual reimagining of GitHub as a fantasy RPG guild hall. The original GitHub workflow stays recognizable, but the design language is completely reinvented: repositories become quest logs, issues become bounties, pull requests become council reviews, GitHub Actions becomes the forge, Copilot becomes the arcane scribe, and open source becomes the guild network. The site includes an interactive quest workflow, a cinematic demo panel, a custom ElevenLabs Guild Master voice guide that narrates the experience, and a Groq-powered “Ask the Guild Master” assistant that explains GitHub concepts inside the fantasy world. Built with v0 for the redesign, ElevenLabs for the voice narration, and Groq for the in-world assistant.

A full UI overhaul of ElevenLabs.io, reimagined as the operating system for synthetic sound. Resonance OS becomes a control surface—telemetric, cinematic, and instrumented. It spans three core experiences: • A landing page with a real-time, audio-reactive TTS demo • A searchable Voice Library where every card plays instantly • A tiered Pricing page with a sticky comparison matrix The standout moment is the hero: type text, choose a voice, hit play—and a lime waveform pulses in sync with real audio. Resonance OS fixes the current experience with three moves: real in-page synthesis demos, a precise visual system (near-black canvas, electric-lime signals, warm-coral accents, mono telemetry), and a voice library where every card is a live demo.

Notion Atlas reimagines Notion as a living paper command desk: docs, wikis, projects, databases, AI summaries, and integrations become a redesigned workspace with live briefs, connected signals, and an ElevenLabs-powered custom voice layer that narrates dense workspaces into clear, actionable updates.

created an animated reskin of ChatGPT, used v0 to code and design it, and used ElevenLabs to add the quirky voices to add to its theme.

This project is an experimental redesign/demo inspired by the clean, polished presentation style of Apple.com, but reimagined through a more dynamic AI-first experience. The current submission is very much a prototype and still needs significant polish, bug fixing, and refinement. Ironically, that contrast is part of what makes the concept interesting: Apple’s design language is known for precision and perfection, while this demo intentionally captures the fast-moving, iterative nature of modern AI product development. Rather than a finished product, this is a proof-of-concept exploring how AI experiences, motion, and presentation layers could feel more immersive, reactive, and emotionally engaging on the web. Built quickly under hackathon constraints, with more focus on experimentation and direction than production readiness.

Singapore Airlines — Concept Site A reimagining of the Singapore Airlines homepage as long-form cinema instead of a fare-finder utility. Full-bleed plane footage, parallax destination strips, Instrument Serif typography, and "liquid glass" surfaces — with the full booking, KrisFlyer, and check-in IA preserved underneath the editorial frame. Built with React 19, Vite, TypeScript, and Tailwind. Static, no backend, deploys to any CDN. ElevenLabs powers two voice surfaces: Live Concierge — A real-time conversational agent (floating button, bottom-right) using @elevenlabs/react. Opens a WebSocket session to an ElevenLabs Conversational AI agent, streams the user's mic up, plays the agent's voice back, and surfaces a live transcript. Users can ask about destinations, fares, baggage, or KrisFlyer in their own voice. Ambient destination narration — Each parallax strip (Bali, Tokyo, Paris, NYC, Sydney, London, Zurich) auto-plays a short cinematic narration when scrolled into view. Generated at build time via the ElevenLabs TTS REST API with tuned voice settings for an editorial delivery, then shipped as static .mp3s — so runtime never hits the API. The split is deliberate: TTS is precomputed and free at runtime, while the live agent is opt-in only when a user engages — keeping the page fast by default.

An interactive Ron Weasley storybook inspired by the Ronald Weasley fandom page (https://harrypotter.fandom.com/wiki/Ronald_Weasley), transforming a static biography into a cinematic, character-driven reading experience. It features an animated book UI and text highlighting that triggers matching Ron-style voice commentary. ElevenLabs powers the voice layer so highlighted passages play back in Ron’s voice, while v0 helped build the product logic, UX, commentary mapping, and interaction flow. To respect copyright, only selected portions of the source material are included rather than the full biography.

Echo Impostor is a procedural social stealth game where ElevenLabs voice AI becomes the central gameplay mechanic. Every run generates a new crew voiced with unique TTS personalities — one is an impostor, and the player must interrogate suspects, listen for vocal contradictions, and collect audio evidence to survive. We extended ElevenLabs far beyond dialogue: contextual voice tutorials teach the player, collectible audio logs reveal ship lore, dynamic room narration builds atmosphere, and proximity alerts warn of danger — all paired with AI-generated music and SFX for a fully immersive, voice-driven investigation.

GitHub Guild turns repos into quest logs, issues into bounties, PRs into council reviews, and Actions into the forge.

Apple website but if it was built in 2026. An AI Chat app where you can buy the products and ask specific questions to the AI (Apple Intelligence).

I redesigned the ElevenLabs homepage in a full Y2K / early-2000s aesthetic using v0 by Vercel — keeping all the original content intact while completely transforming the visual style with Windows XP-style beveled buttons, animated marquee, glowing cyan typography, and retro scanline effects. Then we took it further with ElevenLabs API: a floating Voice Tour button narrates each section of the site using ElevenLabs TTS with a deep synthetic voice, and an interactive Play Demo button lets users hear AI-generated audio directly on the page. Built with: v0 (UI generation + deploy), ElevenLabs TTS API (voice tour + audio demo), Next.js, Vercel.

I redesigned ElevenLabs.io from scratch in Neubrutalism style using v0 by Vercel — bold colors, thick black borders, zero gradients. Same content, completely reinvented design. Then I took it further: I embedded a live ElevenLabs Conversational AI agent (Alex) directly into the page. Visitors can literally talk to the website — ask about pricing, voice cloning, or the API — and Alex responds in real time with AI voice. Built with: v0 by Vercel (React + Tailwind), ElevenLabs Conversational AI SDK (@11labs/react), ElevenLabs TTS for the voice demo section, and ElevenLabs Music for the video soundtrack. Deployed on Vercel. https://v0-elevenlabs-landing-page.vercel.app/