
Challenge
Build and ship a voice-powered app using Replit and ElevenLabs Voice Design or Voice Cloning
Prizes
$7,980 total1st Place
$3,990$3,000 in Replit credits
3 months ElevenLabs Scale ($990)
2nd Place
$2,660$2,000 in Replit credits
2 months ElevenLabs Scale ($660)
3rd Place
$1,330$1,000 in Replit credits
1 month ElevenLabs Scale ($330)
Build a voice-powered mobile or web app using Replit and ElevenLabs' Voice Design or Voice Cloning APIs, then submit a high-quality viral-style video demonstrating what you've built.
Replit is the fastest way to go from idea to app. Whether prototyping or building production-ready apps, Replit lets you securely vibe code any app in plain English with auth, database, security, testing and publishing built into the platform. Use Replit Agent to go from idea to deployed app with AI assistance, and publish your creation as a mobile or web app that anyone can use.
Voice Design lets you create unique AI voices from text descriptions — describe a voice and ElevenLabs generates it. Voice Cloning lets you clone any voice from audio samples. Both APIs unlock creative possibilities for building apps with custom, personalized voices.
We want to see you build in public — share your progress, struggles, and wins as you go. Use Replit Agent to help you build, and push the boundaries of what's possible with AI-assisted development.
We're most excited to see apps that:
Replit's free tier lets you get started immediately. For this hackathon, we recommend using Replit Agent to help you build faster. Use the offer code below for a discount on Replit Core if you need more power.
When posting your submission on social media, tag @Replit and @elevenlabsio and use the hashtag #ElevenHacks.
Attendee offers
Replit Core discount
Use at checkout for $25 off your first month of Replit Core
Sign in to reveal this code
1 month ElevenLabs Creator
Free month of ElevenLabs Creator plan for all attendees
Sign in to claim this offer
Sign in to submit your project
3 Apr, 18:08
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.

4 Apr, 06:59
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.

4 Apr, 00:44
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.

4 Apr, 00:03
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.
