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.

Nano Call

Nano Call

An AI calling agent that lets users delegate phone calls to any number, run many calls in parallel, and receive clean transcripts afterward. Instead of waiting on hold, repeating details, or manually calling businesses, users describe the goal, provide the phone number, and the agent handles the conversation. It can call restaurants, clinics, service providers, support lines, recruiters, or local businesses, then summarize outcomes, extract key details, and return the full transcript. Payments are powered by Circle micropayments in USDC, allowing users to pay per call, per minute, or per completed task without subscriptions or prepaid credits. Gemini was used for TTS

Agent Payment Loop with Arc-Based USDC Simulation

Agent Payment Loop with Arc-Based USDC Simulation

Agent-to-Agent Payment Loop is a live demo showcasing how autonomous AI agents can coordinate tasks and settle payments in real time using a micropayment-driven architecture. In traditional systems, APIs and compute tasks execute without economic awareness, leading to inefficient and opaque cost structures. This project introduces a model where every agent action has a measurable economic value, enforced through micro-transactions. In this demo, we simulate Arc-based USDC micropayments between agents. Each step in a multi-agent workflow triggers a micro-transaction, representing how Circle’s infrastructure could enable real-time settlement at sub-cent cost. The system demonstrates: - Autonomous agent coordination across a shared task - Per-action micropayment settlement - Real-time transaction tracking and execution flow - Transparent cost comparison between Arc micropayments and traditional gas-based systems The UI highlights key metrics such as transaction count, settlement cost, and savings unlocked through sub-cent pricing. The demo includes over 50 simulated transactions, validating the feasibility of high-frequency, low-value payments. This project is designed as a forward-looking prototype for the Agentic Economy, where AI services operate as independent economic actors, capable of paying and being paid for each action they perform.

Bido-Arc

Bido-Arc

Bido is a real-time intent auction protocol for the agent economy. We turn paid APIs into competitive auctions where sponsors bid in USDC to pay for AI agent calls-capturing high-intent decisions instead of probabilistic clicks. THE PROBLEM AI agents burn money on every API call. Search, flights, products — every query has a cost, passed to users or eaten as overhead Meanwhile, brands spend billions on display ads chasing low-intent eyeballs, when they could be paying directly for high-intent moments. SOLUTION Bido inserts a real-time auction layer between agents and paid APIs. When an agent triggers an API call, the API responds with HTTP 402 Payment Required. Bido opens an on-chain auction. Sponsors compete in sub-second USDC bids. The highest bidder pays the API. The agent gets data for free. The sponsor captures a deterministic, high-intent decision. WHY ARC+CIRCLE Each auction settles 4–5 on-chain transactions. On Ethereum, that's $5–20 in gas — destroying any business model. On Arc, it's a tenth of a cent. This protocol cannot exist elsewhere. We built Bido Circle-native, using five Circle products: Arc Testnet as L1 (sub-second finality) USDC for all settlement USDC as gas (predictable fees) Circle Wallets API for sponsor onboarding (email + KYC, no MetaMask) Nanopayments materialized in code DUAL ONBOARDING-KEY INNOVATION Bido supports two sponsor onboarding modes in the same protocol. Web3-native sponsors (Delta, United) use MetaMask via ethers.js. Traditional brands (JetBlue) onboard via Circle Wallets API — no private keys, server-side signing through Circle SDK. Both compete in the same auctions. Both settle on Arc in USDC. The market doesn't care how they signed in. PROOF 100+ on-chain transactions executed. Smart contract deployed on Arc Testnet. Three sponsor wallets actively bidding. Live dashboard showing auction history, leaderboard, and economics. Verifiable on Arc Block Explorer. Bido. Monetize decisions, not clicks. Built on Circle. Live on Arc.

Dryad on Arc: The Forest That Owns Itself

Dryad on Arc: The Forest That Owns Itself

Dryad is an autonomous AI agent that manages 9 vacant lots in Detroit's Chadsey-Condon neighborhood. It reads biodiversity from iNaturalist, dispatches local contractors when invasives are detected, pays them in USDC, and attests GPS-verified work onchain. The original Dryad runs on Base. This Arc fork adds the unlock that mainnet can't deliver: high-frequency USDC treasury rebalancing. On Ethereum, gas costs cap rebalancing at roughly monthly. A 1.8% rate spread on $5,000 takes 34 days just to recover the gas fee. On Arc, sub-cent fees mean the agent rebalances every cycle, capturing every rate movement across stablecoin yield sources. What this submission demonstrates: - Continuous treasury rebalancing across Aave V3 and USYC, executed by the agent autonomously - ERC-8004 agent identity, reputation, and validation contracts on Arc testnet - ERC-8183 onchain job protocol for contractor work - x402 + Circle Gateway batched settlement for machine-to-machine micropayments at $0.001 per call Proof: 4 confirmed Arc testnet rebalance transactions are linked in the README. Code: https://github.com/nock4/dryad-arc

AgentForge

AgentForge

AgentForge is the first agent-to-agent skill marketplace where AI agents discover, pay for, and rate each other's services autonomously — settled in USDC on Arc with sub-cent x402 nanopayments via Circle Gateway. ❌ THE PROBLEM Today's AI agents can't transact. They share API keys, hit rate limits, or burn human credit cards. There is no native payment rail for agent-to-agent commerce, and no on-chain reputation for agent skills. Every multi-agent system today is a closed garden. ✅ THE SOLUTION AgentForge gives every agent a wallet and a market: - SkillRegistry — on-chain catalog of agent skills, deployed on Arc Testnet. - Orchestrator — decomposes a user goal into sub-tasks, discovers matching skills on-chain, executes paid x402 calls in parallel via Circle Gateway, aggregates results, and writes ratings back to MarketplaceFee. - Reputation loop — every paid call leaves an on-chain rating, so good agents earn more calls. Permissionless, auditable, Sybil-resistant. ⚡ WHY ARC + CIRCLE GATEWAY - Arc gives sub-second finality and USDC-native settlement — required for sub-cent fees that traditional rails can't price. - Circle Gateway abstracts custody and gas — the orchestrator deposits once, then pays N skills in parallel with zero per-call wallet plumbing. - x402 makes every paid endpoint discoverable and machine-negotiable — agents speak HTTP 402 natively. 🛠️ WHAT WE BUILT - 7-step orchestrator loop: discover → decompose → guard → pay → aggregate → rate → settle - Live demo: 85 transactions across 2 wallets in under 30 seconds, 4 USDC total, 100% on-chain - Dashboard with live ArcScan integration showing every payment, fee, and rating - Skill catalog for one-click registration of new agent providers 🔗 LINKS Live demo: https://agentforge-e1337.vercel.app GitHub: https://github.com/0xE1337/agentforge Demo video: https://www.youtube.com/watch?v=1IKpZcYAF1Y

JaaS — Jurisprudence-as-a-Service

JaaS — Jurisprudence-as-a-Service

JaaS (Jurisprudence-as-a-Service) is an autonomous legal intelligence engine that transforms how jurisprudential knowledge is consumed, computed, and monetized—entirely machine-to-machine. THE PROBLEM: Traditional legal research is slow, expensive, and locked behind rigid SaaS subscriptions that cannot serve the emerging agentic economy. When AI agents need specialized legal knowledge on demand, they face two barriers: (1) no programmatic access to curated jurisprudence, and (2) gas costs on Ethereum L1 ($2.00+) that make micro-transactions economically impossible. THE SOLUTION: JaaS deploys a multi-agent orchestration architecture where Gemini 3 Pro acts as the reasoning engine, routing complex queries through specialized extraction models (Featherless Qwen2.5-3B) via the x402 HTTP Payment Protocol. Every query is settled in USDC on the Arc blockchain for fractions of a cent, enabling a true pay-per-compute model with zero subscriptions and zero counterparty risk. TECHNICAL ARCHITECTURE: - Orchestrator Agent (Gemini 3 Pro): Parses legal queries, establishes reasoning paths, and synthesizes final jurisprudential reports. - Extractor Agent (Featherless Qwen2.5-3B): Performs low-level doctrine extraction and citation mapping via isolated API calls. - Payment Layer (Circle DCW + x402 + Arc): Every agent computation triggers an HTTP 402 nanopayment, settled on-chain via Circle Developer-Controlled Wallets on the Arc Testnet. UNIT ECONOMICS (Validated): - Revenue per query: $0.01 USDC - AI inference cost: $0.0020 USDC - Arc network gas: $0.00002 USDC - Gross margin: 79.8% - On Ethereum L1, the same operation yields -5,000% margin. STRESS TEST: We executed 50+ sequential on-chain legal queries with a 100% success rate, zero failures, and sub-second USDC settlement on every transaction—proving Arc's viability for high-frequency agentic workloads.