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.

On-device Voice Stress Detection

On-device Voice Stress Detection

Slashh turns your phone into a private, always-on companion that notices when your voice is under stress and offers a calming nudge — entirely on-device, in airplane mode, with no recording and no LLM. Most stress detectors look at only one signal. Slashh is multimodal: it runs two transformer models on the Snapdragon Hexagon NPU at the same time. WavLM listens to how you speak (vocal tension and arousal), while Whisper-Tiny transcribes what you say and a tiny Dreaddit-trained classifier scores the words for stress. A small fusion perceptron combines the two into one confident probability — far more reliable than either signal alone — and only raises a gentle relief nudge when stress genuinely sustains. Everything in the inference loop runs locally via PyTorch ExecuTorch and QNN context binaries; the app declares no INTERNET permission, so audio, transcripts, and scores never leave the device. Built and verified live on a Galaxy S25 Ultra (Snapdragon 8 Elite): two neural models on the NPU, a responsive energy fallback, and real-time relief — fully private by construction.

nuncio

nuncio

Nuncio turns cold outreach into personalized video campaigns using a collaborative multi-agent system built on Band. In a shared room, specialized AI agents research prospects, generate personalization angles and scripts, validate compliance, and produce videos with HeyGen and ElevenLabs. Users can observe agent collaboration in real time, approve creative directions, and track progress through a transparent transcript. Unlike template-based or black-box solutions, Nuncio makes AI workflows visible, auditable, and human-in-the-loop—helping sales teams create personalized video outreach at scale.

BidBand: The RFP War Room

BidBand: The RFP War Room

Answering an enterprise or government RFP is the most painful cross-team workflow in B2B sales: 20–40 staff-hours per bid across sales, experts, writers, compliance and an approver, and roughly half of all disqualifications come not from weak answers but from a single missed mandatory requirement. BidBand drops an RFP into a Band room where five specialised agents work the bid in real time. Maestro parses the RFP and publishes the mandatory-requirement matrix. Scout mines the company knowledge base for proof points. Quill drafts each section and hands it peer-to-peer straight to Gavel. Gavel audits every draft against the matrix and can veto non-compliant work, bouncing it back with findings while you watch the rejection-to-revision loop happen live. Sentinel assembles the proposal, scores 100% requirement coverage, seals a hash-chained audit log, and asks the human bid manager to sign off. Band is the only channel the agents use: every handoff, recruitment and tool call flows through the room as @mention-routed messages and events. The transcript IS the workflow. The originality hook is cross-provider checks and balances: the writers (Maestro, Quill) run on AI/ML API closed-weight models, while the researcher and reviewer (Scout, Gavel) run on Featherless open-weight models. No provider ever approves its own work. The demo voiceover is generated with ElevenLabs. Pure Python standard library, zero pip installs: judges run the entire five-agent flow — including a guaranteed compliance veto — with no API keys (python run.py).

GridAI - DER Coordination Protocol

GridAI - DER Coordination Protocol

Problem Australia has roughly 15 GWh of home batteries and the number is climbing fast. They mostly see the same thing: the National Electricity Market price signal. When price drops in the evening they all discharge at once. Following one shared signal makes a fleet synchronise, and a synchronised fleet builds a new evening demand peak instead of smoothing the old one, while pushing voltage outside legal limits at the edge of the distribution network. This failure mode gets worse as virtual-power-plant deployment scales, because it appears precisely when fleets start coordinating against shared signals. It is a second-order problem that today's market design walks straight into. GridAI's novelty is the diagnosis: desynchronisation depends on fleet-level value heterogeneity, and each voltage breach can be attributed by cause, separating PV-export conditions from battery-herding events so only protocol-induced failures escalate. Solution GridAI is a multi-agent coordination protocol. Four agents, Forecaster, Coordinator, Compliance, and Operator, collaborate through Band as the actual collaboration layer, not a notification wrapper. The Coordinator runs a priority-based dispatch: each battery's slot is allocated from global fleet state using its state of charge and the owner's willingness-to-discharge. The fleet desynchronises through heterogeneity, the diversity in what each battery wants, not through symmetric negotiation. The Compliance agent reviews every plan against AS IEC 60038:2022 voltage limits, flags battery-herding breaches (kept distinct from midday PV-export breaches), and escalates to a human Operator with a full Band-native audit trail. Result: battery-herding overvoltage breaches cut from 471 to 0, fleet synchrony from 1.000 to 0.167. Convergence takes 1 to 2 rounds, runs on existing inverter hardware, and fits the CSIP-AUS standard already mandated in Australia.

SentinelFlow

SentinelFlow

Security teams receive thousands of alerts every day, but investigating each one still requires analysts to manually collect evidence, switch between tools, validate findings, and prepare reports. This process is slow, repetitive, and often leads to inconsistent decisions. SentinelFlow was built to solve that problem using collaborative AI agents instead of a single AI assistant. When an alert is received, SentinelFlow launches a coordinated investigation where six specialized AI agents work together through Band. Each agent has a dedicated responsibility, including triage, threat hunting, validation, risk assessment, red-team challenge, and incident coordination. Rather than working independently, every agent shares evidence, challenges assumptions, and contributes to a common investigation workspace. As the investigation progresses, SentinelFlow continuously builds a live knowledge graph that connects entities, evidence, relationships, attack patterns, and business impact. Every decision remains transparent and explainable, allowing analysts to understand how conclusions were reached. Once the investigation is complete, SentinelFlow automatically generates an executive-ready investigation report containing findings, supporting evidence, risk assessment, timeline, and recommended actions. Every investigation is also stored with a complete audit trail that can be replayed for future review. Our goal is not to replace security analysts but to augment them with a collaborative AI workforce that reduces investigation time, improves consistency, and helps security teams make faster, evidence-backed decisions.

SentinelOps — AI Crisis Command on Band

SentinelOps — AI Crisis Command on Band

SentinelOps is an AI-powered crisis command center built on top of Band's multi-agent infrastructure. When a high-stakes incident occurs — a data breach, financial fraud, ransomware attack, or regulatory emergency — organizations need coordinated decision-making across multiple domains simultaneously. SentinelOps makes that possible in minutes, not hours. Each of the 7 agents is registered as a Remote Agent on Band with its own API key and identity: Incident Commander, Security Agent, Operations Agent, Legal Agent, Finance Agent, PR Agent, and Executive Agent. When a crisis is launched, the Commander creates a Band chat room, adds all agents as participants, and initiates a sequential debate where each agent @mentions the next — creating a fully auditable, traceable decision chain inside Band. Agents powered by Llama 3.3 70B via Groq don't just agree with each other. Security pushes for immediate containment. Operations warns that containment destroys evidence. Legal flags regulatory notification windows. Finance quantifies the cost of every option. The Executive agent synthesizes the conflict into a final directive. The key differentiator is human-in-the-loop intervention. After the initial debate, a human operator can inject new intelligence directly into the Band crisis room. When new information arrives the agents recalibrate their positions in real time and issue updated directives. Every decision, conflict, and directive is logged with timestamps, agent identity, and model attribution — ready for regulatory audit. The full crisis timeline is exportable as a structured JSON report. SentinelOps is designed for Track 3: Regulated/High-Stakes scenarios where getting it wrong means legal liability, financial loss, or risk to human life. Band is not just the delivery layer — it is the orchestration backbone that makes multi-agent crisis coordination auditable and compliant by design.