Hack #3: Replit

FaceTime From Mars 2159 - A voice-powered web app where you call AI colonists living on Mars in the year 2159. - Humans migrated to Mars in 2070. Now, 90 years later, you can pick up a quantum relay and have a real voice conversation with three Mars colonists — each with a unique ElevenLabs voice and AI personality powered by Claude. The colonists: • Zeph (16) — born on Mars, never seen Earth, thinks rain is terrifying • Chef Riku (34) — recreates Earth food from archives, has never tasted pizza • Dr. Nova (41) — terraforming chief, making Mars breathable How it uses ElevenLabs: Each character has a custom ElevenLabs voice ID with tuned settings (low stability for expressiveness, high style for personality). Voice responses are processed through a Web Audio API radio filter with static bursts to simulate a real deep-space transmission. Three distinct voices — a kid, an adult male, and an adult female — make each conversation feel completely different. How it uses Replit: Built entirely with Replit Agent assistance. Backend (FastAPI) and frontend (Next.js) both deployed on Replit as a single project with two workflows. Secrets manager handles API keys. Published as a web app anyone can use. Additional features: 3D interactive Mars/Earth scene (React Three Fiber), walkie-talkie push-to-talk, camera transitions between planets, ambient space sounds, signal glitches, Mars clock, suggested conversation topics, and end-call transmission report.

MyVoice is an AAC (augmentative and alternative communication) app that gives people who can't speak a voice that actually sounds like them — not a robot. Every existing AAC app assigns users a generic text-to-speech voice from a library. MyVoice uses the ElevenLabs Voice Design API to generate a completely unique voice from scratch based on who the user is — their gender, age, accent, and personality. Built and deployed entirely on Replit using Replit Agent, the app guides users through a 4-step onboarding, generates 3 voice previews in real time, and saves their chosen voice permanently via the ElevenLabs TTS API. The result is a fully functional web app anyone can use at myvoice-app.replit.app. The insight that makes this different: the people who need AAC apps most — adults who lost their voice to ALS, stroke, or cancer — are intelligent, expressive people being handed a tool that sounds like a 1990s GPS. Voice Design makes it possible, for the first time, to give someone a voice that feels like theirs. That moment — hearing yourself speak in a voice you chose — is what this app is built around.

StoryDad is a bedtime-story app where parents clone their voice, generate personalized stories for their child, and play them back in that voice. It has a dark navy, starry, amber-glow UI with pages for signing in, recording a voice, generating stories, and listening to them.

Dating today is exhausting. More often than not, we end up choosing people based on a quick glance a photo, a vibe rather than their values. And honestly, that makes sense. It’s hard to truly understand someone without spending time talking to them. But what if we could change that? What if, instead of endlessly swiping, you only interacted with people who genuinely share your values, your energy, and your outlook on life? That’s exactly what we’re building. Our approach starts differently. Instead of leading with photos, we begin by understanding *you*. Through a series of thoughtful, judgment-free questions, we get to know who you are as a person. What are you looking for in a partner? What kind of life do you envision? What are your expectations around career, responsibilities, and compatibility? What are your deal-breakers—your “icks”? These are the things that actually define meaningful connections. Based on your answers, we match you with people who align with your values and mindset not just your surface-level preferences. But here’s where it gets really interesting. We use advanced conversational AI combined with voice cloning to create a personalized version of you an AI that talks like you, sounds like you, and represents your personality. So instead of awkward first chats or forced small talk, your AI interacts on your behalf. When you connect with someone, you’re not just reading text you’re experiencing a conversation. You hear their voice, their tone, their personality. And they hear yours. It feels natural, human, and far more meaningful than traditional messaging. At this stage, neither of you sees each other’s full profile. There’s no pressure, no judgment—just authentic interaction based on who you are. If the conversation clicks if the energy feels right you can choose to like each other. Once there’s mutual interest, both of you unlock the next step: real profiles, real conversations, and the opportunity to take things forward. And if the other person prefers, they can even interact with your AI first before deciding to match making the entire process more comfortable and less intimidating. We’re building all of this using powerful tools like ElevenLabs for voice cloning and conversational AI, combined with an integrated development environment that lets us design, build, and launch everything seamlessly in one place. The result? A dating experience that prioritizes compatibility over appearance, depth over small talk, and genuine connection over endless swiping. Because finding the right person shouldn’t feel like a chore. It should feel like meeting someone who truly gets you.

There's a really big potential problem in the coming future. The end of the world. And if that happens, how would we solve the solutions human need to survive from scratch? WildMind is a living, self-teaching persistent AI simulation where 30 independent AI agents — each a separate language model — are dropped into a procedurally-generated world with nothing. No language. No culture. No shared memory. No knowledge of survival, medicine, agriculture, fire, or each other. We use ElevenLabs to capture the language development. Agents develop proto-words — invented sound-sequences that acquire shared meaning through repeated co-occurrence with context. The sound "kroh-tuh" said near fire enough times, by enough agents, in enough interactions, becomes the tribal word for fire. This emergence follows real mathematical laws: Zipf's Law (word frequency distributions), Heaps' Law (vocabulary growth curves), and small-world network topology — the same patterns that govern every human language on Earth, appearing without instruction. You can listen along as the develop their language thanks to ElevenLabs, on a massive information dashboard where you can track every tick from every world hosted by Replit. The end goal is to publish **A Guide to Restarting Human Civilization** — a living, multimedia document synthesized from simulation data and made available to researchers, institutions, and anyone studying civilizational resilience.

Does your child spend too much time watching and scrolling? What if screen time could become something they actively create? Powered by ElevenLabs’ AI magic, ElevenTales transforms storytelling into a creative, real-time experience where children don’t just listen—they co-create. Stories evolve in real time with rich, dynamic visuals that grow alongside a child’s imagination. Kids can choose a storyteller, pick a theme, show a toy, draw something, or invent a character, and instantly the story adapts. Nothing is scripted. It’s a live conversation where the AI responds to their ideas, questions, and twists as they happen. Each storyteller is powered by ElevenLabs as a real-time conversational voice agent, custom-designed and voice-cloned to give every character a distinct personality, with expressive narration and sound effects. At the same time, Google's Nano Banana generates vivid, consistent illustrations for every scene, building an immersive visual world alongside the story. Built and iterated rapidly on Replit, ElevenTales leveraged quick development cycles and one-click deployments to bring this experience to life. No menus. No interruptions. Just voice, visuals, and imagination flowing together. ElevenTales turns screen time into a space for creativity, curiosity, and expression, where children don’t just hear stories—they build them.

I built an ASMR app that allows users to easily create their own downloadable ASMR audios. Instead of having to rely on YouTube and it's interrupting ads and background play unreliability.

DayCoach is a voice-powered daily accountability app that adapts its coaching style based on how you've been showing up. Instead of passive to-do lists, you have a real conversation with an AI coach every morning and evening — and the coach updates your task list in real time while you talk. The app uses ElevenLabs Conversational AI to power four distinct coaching personas — Sunny, Coach, Commander, and Champion — each triggered automatically based on your streak and completion patterns. You never pick a coach; the app decides based on your recent behavior. Keep your streak and you get warm encouragement. Miss three days and Commander shows up with no excuses. ElevenLabs handles the full voice conversation, including client-side tool calls that let the coach mark tasks complete, add new ones, update vague ones, or delete them mid-session — all reflected live in the UI. The app is deployed on Replit using autoscale, with a PostgreSQL backend (Neon) and a React frontend served from the same Express server in production.

Most of us have thousands of photos of the people we love. But almost no recordings of their voice. VoiceTree lets you clone and preserve the voice of your family members — and build a living archive of their stories, for future generations

VOIDMAZE: A fullscreen 3D sci-fi stealth/combat maze demo built for the ElevenLabs x Replit Hackathon; you pilot a craft through a procedural orbital facility, balancing creeping stealth and offensive laser fire to disable turrets/ emitters and then reach the jump gate. - Gameplay mixes raycast-rendered walls, sprite-like turrets and emitters, and HUD for hull, detection, cooldown, sector info, and remaining hostiles; shooting raises detection and triggers alarms that make defenses more aggressive, while staying quiet keeps the facility calm. - Systems include a player laser with cooldown and hit sparks, rotating turrets that track and fire, wall-mounted emitters, detection meter tied to alarms, Web Audio API feedback (shots, impacts, explosions, alarms), and overlay menus for deploy/pause/results

Typiano is an interactive typing-to-music web application that turns everyday keyboard input into a live audiovisual performance. Each keystroke is mapped to a musical note, layered with synthesized and AI-generated sound textures, and reflected through reactive visuals including floating note effects, stage lighting, phrase tracking, and animated crowd responses. The experience is designed to feel immediate, playful, and performance-driven while remaining lightweight and easy to run. Built with Node.js, Express, and vanilla frontend technologies, Typiano combines a dispatcher-driven client architecture with Web Audio fallback and ElevenLabs integrations for vocal hype reactions and AI note generation. The project is intended as both a polished demo product and a clear, modular codebase that showcases interactive sound design, real-time UI feedback, and lightweight AI-enhanced user experience.

Buddy Teach — AI Language Tutor with Natural Voice Conversations Buddy Teach is an interactive language learning app that teaches 12 languages through real conversations, not flashcards. It uses ElevenLabs Multilingual V2 for natural, expressive text-to-speech that makes the AI tutor sound like a real person — not a robot. How it works: Pick a language, watch a YouTube intro video about the topic, then practice through conversation exercises An AI tutor (powered by Groq's Kimi K2) plays Person A in a real-world scenario — ordering food, greeting a neighbor, asking for directions You speak back as Person B using your microphone (Groq Whisper transcription) ElevenLabs speaks the tutor's lines with the "Alice" voice — clear, warm, and engaging — using mood-based voice settings (celebrating = expressive, teaching = stable, encouraging = warm) Strict evaluation ensures you actually speak the target language, not English After 5 exercises, a vocabulary quiz tests what you learned — all in your native language ElevenLabs Integration: eleven_multilingual_v2 model for high-quality multilingual speech across 12 languages Real-time streaming TTS via the official @elevenlabs/elevenlabs-js SDK Dynamic voiceSettings that change based on mood (stability, similarity_boost, style parameters adjust per context) Serves as the core teaching voice — every phrase, explanation, and feedback is spoken through ElevenLabs Key Features: 12 languages with endless levels that adapt to your skill YouTube video intros matched to each lesson topic Conversation-based learning (two people talking, not memorizing words) Native language support — explanations in Hindi, Spanish, Arabic, etc. Server-side leaderboard and authentication Dark mode UI inspired by Duolingo Tech Stack: React 19, Vite, Express 5, ElevenLabs SDK, Groq (Kimi K2 + Whisper), TypeScript

Stage is an AI-powered public speaking simulator that helps you conquer the fear of presenting. Choose your audience size, mood, and presentation type — then step on stage. The moment you speak, ElevenLabs Voice Design generates real crowd reactions in real time. Stay silent and lose them. Keep talking and earn their applause. When you finish, an AI voice coach designed with ElevenLabs speaks personalized feedback based on your actual performance. Built with Replit and ElevenLabs Voice Design API.

A 3D dungeon where AI-voiced guardians block your path and challenge you with riddles. ElevenLabs Voice Design used to create distinct guardian voices each delivering riddles the player must solve to progress. Built and deployed on Replit as a playable web game.

I built an AI-powered voice travel web application called “AI Voice Travel Companion.” It allows users to plan trips and explore destinations using simple voice or text input. The problem I am solving is that most travel platforms provide static information and require users to search manually. They do not offer a natural, interactive experience or real-time guidance. My solution creates a conversational travel assistant where users can ask questions, get personalized travel plans, and receive instant answers through voice. It makes trip planning faster, easier, and more engaging. The application uses #ElevenLabs for high-quality, realistic voice generation. It converts AI responses into natural speech, allowing users to interact with the system like a real travel companion. I built and deployed the entire application using #Replit, which helped me quickly develop, test, and publish the web app in one place. Overall, this project demonstrates how voice AI can transform travel planning into a more human-like and accessible experience.

Story Seeds generates personalized bedtime stories narrated in a family member's cloned voice using ElevenLabs Voice Cloning for the narrator and Voice Design for story previews. Parents record 30 seconds of their voice. Claude generates a unique story featuring their child's name, favourite toy, and something that happened that day. ElevenLabs synthesizes it in the cloned voice. Every night, a different story. Always in a voice the child loves. Built on Replit using ElevenLabs Voice Cloning API, eleven_multilingual_v2 model, and Replit Auth + Database for per-family personalization.

ToughTalk AI - Practice any difficult conversation before it happens, and hear yourself nailing it. Pick a scenario, an angry customer, a salary negotiation, an aggressive interview, and start talking. The app creates a unique AI character with its own personality, tactics, and a custom-designed voice through ElevenLabs. You practice live, by voice, directly from your browser. The character pushes back, interrupts, and resists just like a real person would. After the session, you get a coaching report with a performance score, your strengths backed by exact quotes, and specific phrases you can use next time. Then comes the magic. Clone your voice with a 30-second recording, and ToughTalk rebuilds the entire conversation as an ideal replay — two ElevenLabs agents talking to each other using the character's designed voice and YOUR cloned voice. You literally hear yourself handling it perfectly. The app uses five ElevenLabs capabilities deeply: Voice Design to create character voices from descriptions, Conversational AI for real-time practice via signed URLs, Instant Voice Cloning from a short sample, Text-to-Speech for replay generation, and a dual-agent backend orchestration where two ElevenLabs agents converse autonomously to produce the ideal replay. Built and deployed on Replit, using Replit's integrated PostgreSQL and object storage.

Imposter Among You is a mystery game where every session generates a fresh case to solve. Players step into the role of a detective, questioning three suspects - each brought to life with unique, realistic voices using ElevenLabs voice design. As you gather clues through conversations, inconsistencies begin to surface, challenging you to think critically and uncover the truth and find the accused. The entire experience was built using Replit Agent 4, enabling rapid development and seamless deployment of this voice-driven investigative game.

OpenClaw is powerful — but chatting with it on Telegram or WhatsApp feels clunky. Open the app, type a command, hit send, and wait. That's not a great experience for something that's supposed to feel like Jarvis. So I built Claw Speaks using Replit. A React Native app that gives OpenClaw a real voice interface. Lock your screen, double-tap your earbuds, and just say "Check my emails" — Claw Speaks sends it to OpenClaw, gets the response, and reads it back to you in a natural voice powered by ElevenLabs Voice Design. Use your OpenClaw while driving, working, or at the gym — a complete hands-free experience. ElevenLabs lets you choose or create a custom designed voice for your agent, giving you a more personalized OpenClaw experience.

▎ REM-MOM is a voice AI application that addresses one of dementia care's most critical challenges: medication non-adherence. 55 million people worldwide live with dementia, and generic reminder apps with robotic voices are routinely ignored by patients. Research shows that familiar voices, especially family members, are encoded in deep procedural memory, the kind that dementia erodes last. ▎ REM-MOM uses ElevenLabs Instant Voice Cloning to let family members create AI-powered reminders in their own voice. A 30-second voice sample is enough to generate medication reminders, morning check-ins, and guided memory exercises that sound like the patient's actual child, not a machine. The backend runs on Node.js/Express deployed via AWS, with ElevenLabs handling voice cloning and multilingual text-to-speech synthesis. ▎ The project demonstrates how voice AI can solve a deeply human problem: helping families stay present for the people they love, even across distance and demanding schedules. Technology should bring us closer, not push us apart.

PodChat transforms podcasts from "one-way listening" to "two-way dialogue"—upload an audio episode, and the system automatically identifies each speaker, clones each person's voice, builds a knowledge base, and generates a whole group of AI host avatars. In monologue podcasts, you can have one-on-one voice conversations with the host at any time; in multi-person podcasts, you can enter group chat mode, ask questions to all members or @ a specific guest for follow-up questions, and each AI character responds to you with their own realistic voice. The product is almost entirely built on ElevenLabs: Speaker Diarization separates speakers, Instant Voice Cloning clones each character, Voice Design API automatically analyzes each person's emotional style based on scripts to generate tuning parameters, Conversational AI WebSocket supports real-time voice calls, and Text-to-Speech drives quick summary reading with emotion switching—one API key runs the entire chain from recognition and cloning to dialogue; the application is deployed on Replit, requiring zero registration, and all data is stored locally in the browser; Firecrawl supplements the knowledge base by crawling web content mentioned in podcasts. Existing podcast AI tools are limited to transcription and summarization, while PodChat allows you to chat with the "host" in person anytime, transforming one-way content consumption into a multi-role, interactive experience with follow-up questions.

Voicinne is an interactive deepfake simulator that functions as a "digital vaccine" against voice cloning scams, utilizing experiential learning to build cybersecurity immunity within families. The platform enables users to clone their voice in just 60 seconds and initiate a harmless, controlled deepfake phone call simulation, utilizing joyful surprises to engage them before revealing. This visceral experience effectively teaches to recognise the risk of potential scams and motivates them to establish some level of safety measures like a family safe-word.

Get pep talks from Future You, the AI that calls you as if it is the person you're trying to become. Future You uses ElevenLabs Voice Cloning to capture your voice, then calls you before your workout as your future self, the version of you who already crushed your goals. It pulls real biometric data from your Fitbit (sleep score, HRV, resting heart rate, active zone minutes) and weaves it into a personalized coaching call. After your workout, Future You calls back with a debrief based on what actually happened. We used ElevenLabs Voice Cloning for the Future You persona, Voice Design for multiple guest coach personalities (drill instructor, zen master, 80s aerobics icon, and a no-nonsense commander), and Conversational AI with ElevenAgents for interactive call sessions. We use overrides for prompts and first messages as well as conversation initiation webhooks for inbound calls. We use Twilio for phone conversations and ElevenLabs API for web conversations. Built entirely with Replit Agent 4 with shockingly few prompts. The moment that makes it real: hearing your own voice tell you "You slept 5 hours and 40 minutes. Your HRV is down. I know you want to skip. I made that call once. Don't, or you never become me." That's not a notification. That's motivation.

Friction is an AI-powered, voice-to-voice simulator designed to pressure-test your professional communication skills in high-stakes scenarios. Static interview prep and mirror-talking don't simulate the one thing that actually makes conversations difficult: human friction. Whether you're navigating a brutal McKinsey case study, pitching a skeptical venture capitalist, or negotiating a higher salary, Friction provides a hyper-realistic environment to stumble, learn, and perfect your pitch before the real thing. Core Features: Hyper-Realistic Voice Opponents: Powered by ElevenLabs API (Voice Design, STT, and TTS), your AI counterpart isn't just a chatbot. It interrupts, pushes back, and reacts dynamically to your arguments with natural cadence and tone. High-Stakes Scenarios: Instantly jump into pre-configured battlegrounds, including FAANG behavioral rounds, startup CTO technicals, freelance rate negotiations, and difficult performance reviews. Adjustable Pressure: Dial the opponent difficulty from Easy up to Brutal to match your target stress level and simulate the intensity of top-tier professional environments. Pre-Flight Strategy: Ground yourself before the session with targeted best practices, such as strict adherence to the STAR method and the 90-second response rule. Deep Performance Analytics: Post-session breakdowns don't just give you an arbitrary score. Friction analyzes your structural logic (e.g., missing a driver-based profit tree in a consulting case) and monitors your speech patterns for hedging words, rating your overall assertiveness and confidence. Built With Replit: For rapid, end-to-end web application development and deployment. ElevenLabs: For Speech-to-Text, Text-to-Speech, and custom Voice Design to create lifelike, high-pressure adversaries.

Gubbins Gets Going is an interactive children's storybook where every character has a unique AI voice, including the child playing it. A 3-year-old records their voice once and becomes the hero of the story through ElevenLabs voice cloning. A character named Gubbins hosts the experience, guiding kids through genre selection and story setup. Stories adapt vocabulary and stakes to the child's age. Every new character gets a unique voice generated on the fly through Voice Design. Sound effects are generated per scene. Kids choose what happens next by speaking or typing. My 3-year-old tested it. A seahorse named Pete introduced himself and my son said "Hi Pete, I'm Ricky." The whisper fish appeared and he said "I like it." That's the whole pitch. Five ElevenLabs APIs in one app: Text-to-Speech, Voice Cloning, Voice Design, Sound Effects, and Speech-to-Text. Built with ElevenLabs, Anthropic Claude, and deployed on Replit. Live: https://storygubbins.replit.app/ GitHub: https://github.com/reddxmanager/gubbins-gets-going

CastForge — an instant AI podcast studio. The app lets users type any topic, pick a show format (Comedy, Debate, Explainer, True Crime, Hot Takes, Interview), customize AI host voices, and generates a fully produced multi-voice podcast episode with sound effects and background music in about 60 seconds.

I built BizRec, a voice-first app that lets business owners track sales and manage inventory just by speaking, no writing needed. As they sell, they simply talk into their phone, and the app records everything in real time and can instantly report stock levels or total sales. It’s powered by "ElevenLabs" for natural, custom Nigerian voice interaction and built on "Replit" to handle the full frontend, backend, and deployment seamlessly.

Vibe System Visualizer is a fullscreen, audio-reactive web application that captures system or tab audio and transforms it into a cinematic, real-time visual experience. Built using HTML, CSS, vanilla JavaScript, Canvas 2D, and the Web Audio API, it features a bass-reactive neon portal, fluid waveform animations, layered particle depth, and dynamic color transitions across purple, blue, and pink tones. Smooth motion trails and responsive rendering create an immersive, high-performance experience. Designed for both aesthetics and usability, the app supports seamless fullscreen entry, real-time audio responsiveness, and graceful retry handling—ensuring a polished and engaging visual experience with any audio source.

Outlaw Voice is a voice-powered AI app that gives real-time, no-BS guidance when you need it most. Most AI tools try to comfort you or tell you what you want to hear. Outlaw Voice is different. It speaks back in a grounded, direct tone designed to cut through noise, emotion, and overthinking. The user simply presses a button, speaks naturally, and receives an immediate response in a custom ElevenLabs voice. The system combines speech input, AI-generated reasoning, and ElevenLabs text-to-speech to deliver responses that feel human, present, and honest. Built and deployed using Replit, the app is fully accessible as a live web experience. ElevenLabs Voice Design/Cloning is used to create a consistent, recognizable voice that reinforces the identity of the Outlaw Philosopher. What makes it unique is not just the technology, but the intention. This isn’t motivation. It’s accountability. It’s designed for real-world moments when someone is stuck, frustrated, or unsure, and needs clarity, not comfort.

Whisper is an app where you point your camera at literally anything — your coffee mug, a plastic bottle, a tree, your own phone — and it speaks to you with a unique AI-designed voice, real personality, and genuine knowledge pulled from the web in real-time. Your coffee mug speaks in a warm, scratchy, world-weary voice: "Another Monday. You always grip me tighter on Mondays. The coffee inside me traveled 6,200 miles from Sidamo, Ethiopia. A woman picked those beans by hand last October. Slow down. Taste it. For her." Your houseplant is passive-aggressive about being in the corner. Your running shoes guilt-trip you about the 11 days since your last run. A 90-year-old tree tells you about the proposal it witnessed in 1987. But here's where it gets powerful: point at a plastic bottle and the OCEAN speaks — in a vast, ancient, tired voice — telling you what plastic is doing to its body, with real statistics, then suggesting the refill station 0.3 miles from you. Point at fast fashion and the cotton field tells you about the sea that was drained to grow it. Environmental awareness through empathy, not guilt.

CAVE is an immersive, browser-native audio experience that transforms a simple voice recording into a cinematic descent into sound. The app places users inside a dark, atmospheric 3D cave rendered entirely with HTML, CSS, and JavaScript, complete with layered rock geometry, drifting mist, reflective cavern light, motion-reactive depth, and a glowing central chamber. With a single microphone permission grant per session, users can speak into the cave and hear their voice return as if it has traveled deep through a subterranean chamber, shaped by distant reflections, long reverb tails, spatial depth, and realistic echo behavior. What makes CAVE compelling is that it delivers the full experience with no framework, no backend, and no external dependency chain. It uses the MediaRecorder API for browser-based voice capture and the Web Audio API to construct a richer acoustic simulation using delayed direct sound, filtered wall reflections, stereo spread, and custom cave-style reverb. The result is a polished interactive project that feels more like a digital sound installation than a demo page: visually dramatic, technically self-contained, and instantly accessible from any modern browser.

No phone memory again because you took one more photo of SirPuffyPants? Like a leg nuzzle, Cat Shots will ask you if you've taken any pictures today and upload them into the cloud storage of your choice. Want to share with other cat lovers? They'll be envious of your purrfect digital scrapbook with narration powered by ElevenLabs.

Creating viral content is a full-time job. Research, writing, recording, captioning — repeated across X, Instagram, LinkedIn, and TikTok every single week. Viral Content Pipeline is a self-hosted AI system that automates the entire journey — from trending topic discovery to published, voiced, multi-platform content. Built entirely on Replit. The pipeline: Discover trending topics via RSS, X feeds, or manual input → Research with AI → Draft ideas → User approves → Generate AI-written scripts, ElevenLabs voice narration, AI images, and platform-specific captions & hashtags → Publish to X, Instagram, LinkedIn, and TikTok. Every piece of content gets its own distinct human-quality voice powered by ElevenLabs Voice AI. No recording studio. No bottlenecks. Just a pipeline that runs while you sleep. Planned and built on Replit in days. ElevenLabs gives the voice. The pipeline does the rest.

Users record a short voice journal entry each day. The app clones their voice, transcribes the entry, uses an LLM to generate a reflective summary/insight, then reads it back in the user's own voice — so it feels like a wiser version of themselves giving advice. Over time it builds a searchable timeline of entries with mood tracking. I MADE A MISATAKE WITH MY SOCIAL MEDIA POSTS BUT I CANT CHAGE THEM TO THE CORRECT LINKS...

● Blog2Video PRO is a full-stack web app built entirely on Replit that replicates the core experience of https://blog2video.app — turning any blog post URL into a short-form video in minutes. Paste a URL, and GPT-4o scrapes the article and writes a scene-by-scene video script. Pick a voice from the ElevenLabs library — or design a custom one using the Voice Design API by describing it in plain English. Hit render, and the app generates an AI voiceover via ElevenLabs, pairs it with DALL-E 3 visuals, and stitches everything into a downloadable MP4. Built using Replit Agent from a single prompt — full-stack React + Express monorepo, PostgreSQL, ElevenLabs TTS, and OpenAI — deployed live with zero manual configuration.

Voice Persona AI transforms any text into speech that sounds like you — your tone, your style, your voice, if Eleven Labs API key given, otherwise Voice Persona AI transforms text into speech using built in speech engine. Record a short voice sample, pick a persona mode, and generate broadcast-quality audio in seconds. Powered by ElevenLabs voice cloning and an AI script engine with a 6-model OpenRouter fallback chain, it works even without an API key using the built-in system voice. Key features: 🎙 Voice Cloning — Record 15s of your voice; ElevenLabs clones it instantly 🎭 3 Persona Modes — Natural, News Anchor, and Storytelling styles 🎛 Emotion Engine — Calm, Energetic, Serious, or Happy delivery ⚡ Creator Mode — Enter any topic, choose a content type (Reel, News, Speech, Podcast) and tone, and get an AI-written script converted to your cloned voice in 3 steps 🤖 AI Script Refiner — Enhance your own writing or generate ready-to-speak content via AI 📜 History — Every generation saved locally, filterable by Studio, Creator, or audio clips 📱 PWA-first — Installable on any device, works fully in the browser Travel Talk: Translation engine — A new /ai/translate endpoint on the API server uses the same OpenRouter free-model chain to do professional-quality translation between any two languages. 🌍 18 language pairs with flags — English, Spanish, French, German, Japanese, Chinese, Korean, Arabic, Hindi, and more Swap button — instantly flip source and target languages Speak Out / Listen Back mode toggle — clearly separates your voice from theirs Pulsing mic button — push-to-talk using the browser's built-in Speech Recognition API (works in Chrome on Android and Safari on iOS) Real-time status feedback: Listening → Translating → Tap to speak Original + Translation displayed side by side with a "Speak Translation" button (uses system TTS in the correct language voice) Quick Travel Phrases panel — 8 common phrases that auto-translate in one tap.

AdDroid generates fully voiced comedy clips where R2D2 and C3PO debate any two topics in the style of classic Mac vs PC ads. Users input a comparison, GPT-4o writes a witty back-and-forth script, and ElevenLabs brings it to life using Voice Design for distinct, character-accurate voices. Each line is synthesized and streamed seamlessly to feel like a real conversation, paired with animated droids in-browser. The entire app was built end-to-end using Replit Agent v4, with PostgreSQL caching to make repeat generations instant and cost-efficient. Every clip is instantly shareable via a unique link.

Voice Lingo turns speech into intelligent, natural-sounding AI interaction using ElevenLabs Voice Design technology.

What we built FieldVoice — an AI phone research platform that deploys voice agents to call real businesses, ask questions naturally, and turn responses into structured data in minutes. Problem it solves Traditional field research is slow, expensive, and hard to scale. Calling hundreds of businesses manually takes days and costs thousands — FieldVoice does it in minutes for a fraction of the cost. How it works (ElevenLabs + Replit) Built entirely on Replit — backend, orchestration, and deployment Uses ElevenLabs for ultra-realistic voice agents: Voice cloning → consistent agent identity (e.g. “Alex”) Voice design → tailored accents, tone, personality TTS → natural, human-like conversations on calls AI handles the full loop: calling, conversing, extracting answers, and structuring the data instantly

A platform that powers Elevenlabs agents to edit and translate audio and vedio and assistance for optimize the market from different platforms

I built CodeMapAI, a tool that turns a GitHub repository or uploaded ZIP file into an interactive visual code map with AI-powered explanations, learning paths, flow understanding, and voice-assisted navigation. It solves a common problem developers face when opening a new or large codebase: it’s hard to know where to start, how files connect, and what each part actually does. Instead of reading everything manually, CodeMapAI helps make the structure and purpose of the codebase much easier to understand. ElevenLabs is used for voice features, specifically text-to-speech, so the app can speak responses and explanations back to the user as part of the voice-assisted experience. Replit was used as part of the building workflow and development environment to help prototype, develop, and iterate on the project faster.

DramaGen is a full-stack web app where you sign in, type a calm, everyday message (for example, “please do your dishes”), choose a drama mode (rage, passive-aggressive, telenovela, disappointed parent, corporate fury, and others), and get back an over-the-top “rant” as playable, downloadable audio—not just text. Problem it solves: Most of us don’t actually want to send a real angry message, but we do want to vent or joke with friends in a way that lands. DramaGen turns “I’m too tired to argue” into a shareable audio clip that feels personal and funny instead of flat text. ElevenLabs: I use Instant Voice Cloning so users can record a short sample and hear the dramatic script in their own voice, plus Voice Design for preset character voices (chef, CEO, telenovela star, etc.). The final line is synthesized with ElevenLabs text-to-speech so every mode sounds like a performance. Replit: The project was built and deployed in the Replit ecosystem—fast iteration from idea to a published web app others can try, with secrets, hosting, and a workflow that matches how Replit is meant to ship voice-powered products end-to-end.

Exit Coach is a secure, voice-first rehearsal app that helps managers practice high-stakes terminations before the real conversation happens. It creates private, realistic role-play sessions where users can speak in their own cloned voice, receive real-time coaching, and review an improved replay to sharpen delivery, empathy, and confidence. Built with Replit Agent 4 and powered by ElevenLabs voice technology, Exit Coach combines realism with privacy through ephemeral sessions and a biometric consent gate. It also includes an Emotion Arc visualization to show how the conversation is landing over time, helping leaders prepare for one of the hardest moments in management with more clarity and humanity.

Ghostwriter AI – A text-to-speech app that almost worked (but I shipped anyway) So here's the story. I joined ElevenHacks because I wanted to build something cool with ElevenLabs' voice API. My idea was simple: an app called Ghostwriter AI. You type or paste any text – notes, a script, a random paragraph – pick a voice, and the AI reads it out loud like a ghostwriter who speaks instead of writes. I thought it would be useful for students who learn better by listening, or anyone who just wants to hear their text in a realistic voice. I spent hours building the frontend. Got the UI looking clean. Added a dropdown menu with different voice options. Made a text input area that actually looks decent. Built an audio player that was ready to play the generated speech. Everything was working perfectly on the design side. Then I tried to integrate the ElevenLabs API. And that's when things fell apart. The Replit Core discount code – the one that was supposed to give free API credits for hackathon participants – kept showing "invalid or expired". I tried it so many times. Typed it carefully. Copied and pasted it. Restarted my repl. Restarted my browser. Even restarted my laptop like that would magically fix it. Nothing worked. The code was dead. No discount code = no API credits = no valid API key. My live app couldn't make any API calls. All that work and the core feature was broken. I felt like giving up. But then I thought: hackathons aren't just about perfect working demos. They're about showing what you can do, even when things go wrong. So I recorded a full demo video. In the video, I walk through the entire app – the UI, the voice selection, the text input, and I explain exactly how the ElevenLabs API would generate speech if I had a working key. The video proves the concept is real, even if the live site can't call the API right now. You can watch the demo here: https://youtu.be/UVw-TDGchUw The code is all on GitHub. It's messy, it's student code, but it's mine. You can see the API integration logic, the frontend, everything. I also tried to deploy it on Vercel, but without a valid API key, the live demo just shows errors. So the YouTube video is my real submission. What did I learn? That shipping something – even a demo video and a half-working app – is better than shipping nothing. That expired discount codes and broken API keys are just part of the student dev experience. And that if you can build under pressure with free tier limitations, you can build anything. Thanks to ElevenLabs for the challenge and Replit for the dev environment (even if that discount code hurt my feelings). Next hackathon, I'm bringing my own API key. Links: Demo video: https://youtu.be/UVw-TDGchUw GitHub repo: https://github.com/Niraj123kumar/ElevenHack_3_Replit #ElevenHacks #GhostwriterAI #StudentDev

CastVoice is a cinematic story-to-audio-drama platform that transforms written stories into fully produced audio experiences. Each character is assigned a distinct voice, scenes include contextual sound effects, and the final output is a fully mixed audio drama. Characters can be cast using AI-designed voices, cloned voices, or by inviting others to contribute voice recordings. What problem does it solve? Producing high-quality audio storytelling traditionally requires voice actors, sound design, and manual editing across multiple tools. Existing AI tools focus primarily on text or single-voice output and do not support multi-character storytelling or end-to-end production. CastVoice addresses this by automating script structuring, voice generation, sound design, and audio mixing, while enabling collaborative storytelling through shared voice participation. How does it use ElevenLabs and this week’s sponsor? ElevenLabs powers the core audio pipeline, including text-to-speech generation with emotion-aware delivery, voice cloning, and contextual sound effect generation. Each character’s dialogue and scene audio are generated and combined into a single, cohesive audio output. Replit is used for building, running, and deploying the full-stack application, enabling rapid development and integration throughout the project.

Lingua Voice is a voice-based language learning PWA where users clone their own voice via ElevenLabs, then practice speaking a target language with an AI tutor that listens, responds, and speaks back in that same cloned voice. Each user gets a personalized 7-day curriculum generated by GPT-4o-mini based on their language, level, and goal, with lesson phrases they can hear pronounced in their own voice before recording. The platform uses ElevenLabs Scribe for speech-to-text, OpenRouter for AI chat, and Clerk for authentication — all wired into a React + Vite frontend backed by an Express + PostgreSQL API. It runs in demo mode with a 20-user cap and one curriculum per account to keep usage controlled during the preview.

VoiceVault helps people facing voice loss preserve their voice in under 5 minutes — and have real conversations with it. Traditional voice banking requires reading 350–1,600 robotic sentences in a clinical setting. Most people give up or never start. VoiceVault replaces that with 7 natural guided prompts — tell us about your favorite meal, share good news, comfort a friend. You sound like yourself because you ARE being yourself. One tap creates an instant voice clone via ElevenLabs Instant Voice Cloning API. The killer feature: Conversation Mode. Every existing voice tool is one-way — you type, it speaks. VoiceVault is the first to close the loop. It LISTENS to the person talking to you using Web Speech API, generates smart response suggestions using AI, and speaks your chosen reply in your cloned voice. It's not just voice preservation — it's conversation preservation. Also includes: one-tap quick phrases for daily and medical needs, smart phrase expansion ("cold" → "Hey, could you grab me a blanket?"), and voice message sharing with loved ones. Built entirely on Replit using ElevenLabs Voice Cloning + TTS APIs. Accessibility-first: WCAG AA colors, 48px+ tap targets, full keyboard/screen reader support. Live demo: voice-vault-cajpany.replit.app https://youtu.be/7Dq4_xUpDkQ

SwarmCast is a voice-powered public sentiment simulator that lets you paste any announcement, press release, or article and instantly hear how 25 diverse AI personas would react in their own voices. It uses ElevenLabs to give each persona a distinct human voice, Replit to build and deploy the full app, and a multi-stage analysis pipeline with live streaming, fact-checking, and an audio “focus group podcast” to forecast sentiment, viral potential, and narrative fracture points.

Social Sim Studio is a voice-first simulation tool that lets students practice real conversations before they happen. Most communication practice happens in controlled environments, but real life is unpredictable. Students don’t struggle because they don’t know what to say. They struggle because conversations don’t follow a script. This tool creates realistic, voice-driven scenarios where students can rehearse everyday interactions like ordering food, asking for help, or joining a conversation. The system responds in real time, asks for clarification when communication is unclear, and adapts tone based on personality and difficulty. Instead of static prompts, students interact with dynamic characters that behave like real people. I used ElevenLabs to power adaptive voice interactions. Each character’s voice changes based on friendliness, supportiveness, and pacing, allowing the same scenario to feel completely different depending on context. This creates a more realistic and flexible practice environment. Custom scenarios allow educators to tailor interactions to individual students, including setting, communication partner, and goal. The system then generates both the conversation logic and voice behavior dynamically. The result is a safe space to practice real-world communication in a way that actually prepares students for real situations. Built by a special education administrator for special education teachers and service providers to use with students who have challenges with communication and social interactions. Social Sim Studio provides a scaffolded way for students to practice conversations in simulated real life scenarios.

What you built: Tiny Funeral is a web app that holds a real ceremony for the trivial things you should have let go of months ago — an abandoned Duolingo streak, a side project that never shipped, a skincare routine, a situationship. You write what you're laying to rest, pick who delivers the eulogy, and within 15 seconds you hear a full spoken ceremony performed in a voice that means it. How I used the tech: Every ceremony voice is generated via the ElevenLabs Voice Design API from a character description — no stock library voices. Five custom voices, each with a distinct physical profile (an 80-year-old Baptist chaplain, an Italian operatic romantic, a British deadpan cynic, a bereaved American father actively weeping, an Irish publican three pints deep). Each voice also runs on its own tuned TTS parameters so the delivery matches the character, not just the timbre. Eulogies are written per-character by Claude (claude-sonnet-4-5) with SSML pause markers baked in so the TTS honors real dramatic pauses. The full app was scaffolded and deployed on Replit. What makes it special: The joke isn't that you're grieving something trivial. The joke is that the ceremony takes the trivial completely seriously. The gap between the subject ("my Duolingo streak") and the delivery (a weeping 40-year-old struggling to finish a sentence) is where the product lives. People come for the joke and stay because they actually needed to let something go.

I just shipped VoiceCast for the @ElevenLabs hackathon — a tool built for indie game developers who want unique character voices without hiring voice actors. Here's how it works: 1. Describe your character's voice (accent, tone, personality) 2. Enter 3–5 lines of dialogue 3. VoiceCast uses ElevenLabs' Voice Design API to generate a unique voice — then synthesizes each line 4. Download a ready-to-use voice pack (.zip).Whether you're making a dark fantasy RPG, a sci-fi shooter, or a cozy town sim — your characters deserve to speak.

Summify is an innovative, AI-powered study companion that transforms the traditional learning experience by converting dense textbooks and complex subjects into engaging, character-driven audio lessons. By leveraging a sophisticated "Tri-Model" AI pipeline, the platform uses Google’s Gemini to analyze content from PDFs or text inputs and draft natural, conversational scripts, which are then brought to life by ElevenLabs’ high-fidelity voice synthesis. Users can choose from a diverse roster of built-in personas—such as a structured Professor, a gritty Detective, or a reflective Philosopher—to tailor the tone of their study session, or even utilize "Debate Mode" to hear two characters discuss a topic from multiple perspectives. Beyond these presets, the app offers advanced customization through Voice Design, allowing users to create unique characters from text descriptions, and "Copy My Voice," a powerful voice cloning feature that enables students to hear their own digital twin teach them the material for maximum focus. Designed for global accessibility, the app supports fourteen languages, all while maintaining a persistent history tab for offline listening. Built and deployed entirely on Replit, Summify represents a seamless integration of modern "vibe coding" and cutting-edge generative AI, effectively turning dry academic material into a personalized, immersive audio journey.

I tried one-shotting my #elevenhacks project with @repl.it If you're cloning your voice with @elevenlabsio, why not learn along the way so both you and your clone improve together?

I built The Apology You Never Got. Some people hurt you and never said sorry. Maybe they passed away. Maybe they just never will. That silence stays with you. This app lets you hear the apology anyway. You upload an audio clip of that person or record a voice impression, type what you wished they had said, and the app plays it back in their cloned voice, word by word. We use ElevenLabs Instant Voice Clone to capture the person's voice from just a short audio sample, and ElevenLabs v3 to speak the apology back with real emotion, in over 70 languages including Hindi and Telugu. The AI writes the apology, the voice makes it feel real. It is not therapy. But sometimes just hearing it is enough.

AI podcast generator that turns any topic into a full two-host podcast episode with custom-designed voices.

If the world as we know it ends, what does starting over from scratch look like?

Ever wanted to hear your favorite artist's voice on a song you wish your artist was on? Or you just hear a voice so good that you want to see what it would sound like on your favorite song? Using ElevenLabs and Replit I built an application that clones your artist's voice on youtube/tiktok and then replaces it with the artist's voice on the song you want to sample. All done through Replit.

The app — AI Language Tutor: 8 language tutors pre-loaded — Sofia (Spanish), Marco (Italian), Claire (French), Hana (Japanese), Felix (German), Ana (Portuguese), Min-jun (Korean), and Yuki (Chinese). Each has a distinct personality and crafted voice description Conversation screen — type to your tutor and get back streamed responses in real time, with each tutor adapting their mix of English and target language to your level Audio playback — once you add your ElevenLabs key, every tutor message gets a speaker button to hear it spoken in their unique AI-designed voice Session history — all your practice conversations are saved and resumable Progress dashboard — tracks sessions, messages, streak days, and favorite language

EchoPersona is a voice-powered AI app that lets you create and talk to personalized AI voices. Instead of just reading text replies, you actually hear responses in a voice you design yourself. It could be a supportive coach, a funny friend, a calm therapist, or even your own cloned voice. Using ElevenLabs Voice Design and Voice Cloning, you can either describe a voice in a few words or upload audio samples to recreate a real one. Once your voice is ready, you can start chatting with it like a real conversation, with responses generated by AI and spoken back to you in that custom voice. What makes the app special is how shareable it is. You can turn conversations into short audio or video clips with captions and waveform visuals, making it easy to post on TikTok, Instagram, or other platforms. It turns simple chats into content people actually want to share. The app is built with Replit, making it fast to go from idea to a fully working product. It has a clean, mobile-friendly interface and includes fun personality presets like startup coach, roasting friend, or motivational trainer to make interactions more engaging. EchoPersona is designed to feel real, personal, and fun to use. It is not just a project, it is something people can actually enjoy, share, and come back to.

HearHome helps parents and older loved ones feel closer to family when distance, language barriers, or loneliness make everyday life harder. A family member sets up a private link with their ElevenLabs voice, and the elder opens a super-simple page, taps one giant button, and gets a warm spoken reply in a familiar voice. Built on Replit and powered by ElevenLabs, it turns voice AI into something comforting instead of confusing.