Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

ElevenLabs

ElevenLabs is a voice technology research company, developing the most compelling AI speech software for publishers and creators. The goal is to instantly convert spoken audio between languages. ElevenLabs was founded in 2022 by best friends: Piotr, an ex-Google machine learning engineer, and Mati, an ex-Palantir deployment strategist. It's backed by Credo Ventures, Concept Ventures and other angel investors, founders, strategic operators and former executives from the industry.

General
Release date2022
AuthorElevenLabs
TypeVoice technology research

Products

Speech Synthesis

Speech Synthesis tool lets you convert any writing to professional audio. Powered by a deep learning model, Speech Synthesis lets you voice anything from a single sentence to a whole book in top quality, at a fraction of the time and resources traditionally involved in recording.

VoiceLab

Design entirely new synthetic voices or clone your own voice. The generative AI model lets you create completely new voices from scratch, while the voice cloning model learns any speech profile from just a minute of audio.

Resources

Useful resources on how to build with ElevenLabs

ElevenLabs - Helpful Resources

Check it out to become a ElevenLabs Master!

Edit on GitHub

ElevenLabs AI technology page Hackathon projects

Discover innovative solutions crafted with ElevenLabs AI technology page, developed by our community members during our engaging hackathons.

ReproForge Sentinel — Claim-to-Evidence AI

ReproForge Sentinel — Claim-to-Evidence AI

AI systems can generate benchmark claims, model promises, and technical demonstrations faster than teams can verify them. ReproForge Sentinel closes that trust gap by turning an AI/ML claim into structured, inspectable evidence. A user submits a repository URL, the exact claim, a runtime target, and declared security policies. ReproForge evaluates the available claim metadata and policy signals, applies deterministic ShadowGuard risk and reproducibility scoring, records a trace of the evaluation, and produces a Reproducibility Passport. The Passport contains the verdict, evidence chain, missing proof, blocked actions, integrity hashes, security notes, and exportable JSON/PDF results. The hackathon build combines a premium React and TanStack interface with a FastAPI backend, Docker packaging, tests, proof schemas, and AMD/Gemma integration adapters. It also includes an AMD ROCm capture workflow that accepts hardware evidence only when device identity, HIP/ROCm, AMD SMI telemetry, workload metrics, and artifact hashes are successfully captured. Our guided sample is clearly labeled and designed for a reliable judge walkthrough. The current public MVP evaluates submitted claim metadata and declared policies; it does not yet clone or execute arbitrary repositories. Real Fireworks/Gemma inference and direct AMD ROCm telemetry remain explicitly marked pending when verified runtime provenance is unavailable. ReproForge never replaces missing measurements with invented proof. ReproForge is not a “truth machine.” It is an evidence machine: a verification layer for AI teams, security reviewers, researchers, investors, and judges who need to understand what was checked, what passed, what failed, and what still cannot be proven.

TURF — AI-Powered Urban Territory Fitness App

TURF — AI-Powered Urban Territory Fitness App

TURF transforms your city into a battlefield. Every run, walk, or cycle is a conquest mission. Our GPS loop-detection algorithm converts movement into claimed territory. Run a closed loop around any block and that land becomes yours, stamped with your profile picture, visible to everyone on a live 3D map in real time. This is not a fitness tracker. This is urban warfare gamified. Powered by AMD compute via Fireworks AI, TURF delivers three AI features. The AI Coach analyzes live GPS data and delivers real-time tactical voice coaching using Gemma model on AMD hardware. AI Route Intelligence processes city heatmaps from millions of GPS pings to recommend optimal routes before each run. AI Weekly Summary generates personalized performance narratives every Sunday driving daily retention. Test the fully functional Android app here: https://drive.google.com/file/d/1YT0vgE1gFM_jcpDHN5UaDwjeU8JEE2jb/view?usp=sharing Note for judges: TURF is a native iOS and Android app. Advanced real-time 3D Mapbox SDK and live GPS territory tracking require mobile only. Features built across eight production phases: Live GPS tracking with real-time route drawing. Territory capture with 200 meter zones. Organic territory claiming where GPS loops become permanent polygon land ownership with profile picture fill pattern on public map. Real-time group runs with live friend location sharing. Social activity feed. Friends system with discovery. Clubs and squads with leaderboards. Five-category global leaderboards. Community challenges with XP rewards. Twenty achievement badges. Personal fitness goals with automatic progress tracking. Real-time push notifications. Full XP leveling system. Built with Flutter, Supabase with PostGIS, Mapbox 3D SDK, and Fireworks AI on AMD Developer Cloud. Pakistan has 120 million people under 35 with fitness app penetration under 3 percent. TURF is the category creator for South Asia. AMD powers every AI decision TURF makes. TURF. Claim your ground.

AgentReplay — time-travel debugger for AI agents

AgentReplay — time-travel debugger for AI agents

When an AI agent does something wrong, "read the logs" isn't debugging — you get a wall of text and no way to ask "what if this one step had gone differently?" And re-running the agent just produces a different conversation; the one that actually broke is gone. AgentReplay treats agent runs like flight data. A Python SDK records every LLM call, tool call, and state change as the agent runs — two-line integration, agent logic untouched. The dashboard lays the run out as a timeline. AI root-cause analysis points at the exact step that broke. Then you fork: replay from that step with a fix applied — live inference, temperature 0, tools sandboxed — into a new run that carries a parent_run_id, while the original stays immutable. A side-by-side compare shows the broken run against the fixed one, on the same conversation, with no real-world side effects. The demo is a real failure mode from my production lead-qualification agent, Nestaro: it booked a caller for Friday when they asked for Saturday. That run is replayed through the recorder — AgentReplay flags step 2 as the culprit and forks a corrected replay that books Saturday, proven side by side, without touching the real booking system. Stack: Python SDK · FastAPI + SQLModel + NeonDB (JSONB event store) · Next.js dashboard. Hosted analysis runs on OpenRouter, provider-swappable via env vars. AMD: AgentReplay's ROCm/PyTorch stack ran on an AMD Radeon gfx1100 (RDNA3, 48 GB), and its real, unmodified root-cause prompt was executed through Gemma 3 4B resident on the AMD GPU — full evidence committed in the repo's amd/ folder.

Kernel Sense

Kernel Sense

Kernel Sense is an autonomous 4-agent AI Lab, built by Team Reason AI System, that predicts GPU kernel performance using AMD compute to optimize AMD compute. Tuning GPU kernels traditionally means brute-force benchmarking every candidate configuration on real hardware — slow and expensive. Kernel Sense trains a model that predicts a configuration's runtime without running it, so only the most promising candidates need to be benchmarked live, cutting most of that brute-force cost out of the workflow entirely. Unlike a fixed AutoML pipeline that hands you a black-box model and a score, Kernel Sense is built so every agent justifies its output, not just produces one. Four LangGraph agents — Analyst, ML Engineer, Critic, Chief Scientist — collaborate autonomously: the Analyst explains why it made each preprocessing decision, the Critic actively judges whether the winning model is trustworthy and can reject its own pipeline's result and trigger a genuine retry loop, and the Chief Scientist synthesizes a business-ready deployment verdict grounded in real computed metrics rather than a templated summary.

ISEEKAIGO

ISEEKAIGO

Most AI companions today are built around static prompts layered on top of large language models. They can generate impressive responses, but they rarely evolve beyond the conversation in front of them. ISEEKAIGO is building the next generation of AI companionship by combining generative AI with persistent memory, human-inspired needs, autonomous behavior, and evolving cognition. Instead of simply responding, our AI learns from experience, self-learning, adapts over time, and develops its own behavioral context, making every interaction more personal and meaningful. Our vision extends beyond creating a better chatbot. We are building a foundation for Human-like AI that can interact with people over long periods while becoming increasingly capable through experience. By breaking this vision into scalable milestones, we aim to transform AI companionship into a platform for future autonomous AI applications such as building physical-AI core. We believe this project represents a meaningful step toward the future of Human-like AI, combining ambitious research with the ability to ship real products and bring advanced AI experiences to millions of users.

PrismLearning.AI: The Agentic Study Partner

PrismLearning.AI: The Agentic Study Partner

Most "AI study tools" are the same thing in a different skin: dump in a PDF, get flashcards or a chatbot that answers questions. PrismLearning.AI is built to actually teach. Upload a PDF, PowerPoint, or YouTube video and it's restructured into a chapter-by-chapter curriculum, taught by Lumi — an agentic tutor that returns structured JSON instead of raw text, so the AI physically drives the UI: scrolling to the right concept, unblurring locked sections as mastery is proven ("Fog of War"), and spawning flashcards mid-conversation. It won't just hand over answers; it scaffolds, asks the student to teach concepts back, and takes voice input directly. Assessment goes deeper than multiple choice: quizzes include real math (LaTeX) and code questions, graded properly, with a confidence check before every reveal. Flashcards run on real spaced repetition, and mastery decays if you don't return — progress reflects retention, not a checkbox. Mastering a chapter triggers a timed boss-battle exam; XP, streaks, and a shareable mastery certificate make study worth returning to, and the app always surfaces what to review next. Under the hood: tutoring runs on gpt-oss-120b via Fireworks AI's serverless platform, powered end-to-end by AMD Instinct GPUs. Flashcards run on a second, smaller model — Gemma 3 27B — deliberately matched to a short templated task instead of over-provisioning one large model everywhere. A gated Enterprise path flips tutoring itself onto a dedicated Gemma 4 deployment for organizations needing full data residency. Built solo by a first-year BSIT student as a first real SaaS attempt — full demo video, live deployment, and documented architecture included.