Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
A voice debrief agent for anti-trafficking caseworkers. Code saves a proposed field only when the caseworker’s words support it, it is read aloud, and the caseworker confirms it. “I think” is labeled as inference, not evidence.
A live 3D digital twin that talks — an AssemblyAI Voice Agent lets security staff and occupants manage real building emergencies: block exits, calculate safe routes, and report hazards, all by voice, with the 3D view updating instantly.
Voxely is a real-time voice assistant powered by AssemblyAI that converts speech to text, understands natural commands, searches the web, opens websites, and performs browser actions through voice.
Context-aware realtime subtitles you can correct and teach by voice, powered by AssemblyAI Realtime STT and Qwen-assisted correction.
Ripcord is a reliability layer for voice agents that detects uncertain or inconsistent critical information, pauses risky workflows, and asks targeted clarification questions before a misunderstanding becomes a real-world action.
Fluenta is a voice AI language tutor built on AssemblyAI's Voice Agent API. Learners practice Spanish, English, French and German through spoken role-plays, with a tutor that adapts its patience to their level and never cuts them off mid-thought.
A speaking-first language app that finds what you can already say, teaches only what your real goal needs, and lets you practise live with real people, with AssemblyAI listening as the evidence engine behind every step.
A real-time voice AI companion that lets you discuss any topic naturally, ask questions, simplify or go deeper, and challenge ideas through adaptive counter-questions, with live web search and sentiment-aware conversations.
NovaFuse is a voice-first AI study partner & STAR mock interview studio. Practice active-recall quizzes and technical interviews through real-time bidirectional voice conversations with adaptive difficulty and automated weak-topic tracking.
An AI reading coach, that listens to every child read aloud in real time, helps them when they're stuck, talks with them about the story afterward, and never marks a mistake it isn't sure about, giving teachers and parents a complete running record.
AI-powered sign language learning with interactive lessons, real-time sign recognition, smart quizzes, speech translation, and personalized progress tracking—making communication more accessible and engaging.
SnapMind AI is an intelligent, privacy-first study assistant that uses on-device AI to provide document Q&A, vision, voice interaction, and personalized learning support—helping students learn faster while keeping their data secure.
AI Debate Arena is a voice-first adaptive debate platform where users defend their positions against an AI opponent. It analyzes arguments, rebuttal handling, clarity, and persuasion, then delivers personalized coaching and practice exercises to improve.
A student skill-exchange platform where people teach what they know, earn Skill Credits, and use them to learn from others—without exchanging money.
BOB / FORGE is an AI-powered multi-agent coding assistant that generates, reviews, tests, and repairs software in a secure sandbox.
RepoPilot 2.0 helps developers understand unfamiliar GitHub repositories faster by generating a codebase X-Ray, answering evidence-backed questions, identifying relevant files, and turning development tasks into actionable implementation plans.
BugRep-AI turns a plain-English bug report and a codebase into a verified, human-approved code repair — powered by IBM Bob agents, proven by real tests, and shareable to Jira, Slack, or Teams.
AI-assisted debugging workflow built with IBM Bob 2.0 that investigates bugs, uses parallel agents, applies fixes, verifies tests, performs code review, and generates structured reports and productivity metrics.
VOCES is a voice-first language immersion app that helps people learn by actually speaking. Users practice through natural AI conversations, receive corrections after each session, and strengthen weak vocabulary through smart review.
LinguSim is a voice-first language learning coach that puts users into dynamic real-world situations, adapts conversations to their responses, evaluates their communication, and personalizes what they practice next.
Zabaan AI is a voice agent for bank customers who mix Urdu and English. Built on AssemblyAI's Voice Agent API, it turns a spoken complaint into a ticket and files it only after the caller confirms the details.
CoAct is a bimanual robotics system where two embodied agents independently interpret spoken instructions, detect disagreement before acting, and use real-time Speechmatics voice correction to safely resolve ambiguity before physical commitment.
A multimodal Physical AI system using dual SO-101 arms, MuJoCo simulation, vision-language reasoning, and bimanual task planning to autonomously set a dinner table from natural-language commands.
A real-time voice bridge for people whose speech is hard for others to understand: people with dysarthria, and people speaking with Parkinson's disease, ALS, cerebral palsy, Down syndrome or after a stroke.
An AI security and compliance officer for SMBs that combines live camera vision and text to detect risks, reason over company policies, and autonomously trigger documented actions.
Vocalis is an AI-powered communication practice platform that helps users become better speakers through deliberate practice, real-time analysis, actionable feedback, and personalized improvement insights.
Sabaq makes mixed Urdu-English lectures searchable by restoring technical terms that speech-to-text writes inconsistently, then adds transcript-based voice Q&A. In our tests, searchable term recall rose from 16% to 79% for new speakers.
Tourist Translator AI is a lightweight, browser-based two-way voice translation app built for instant live communication, utilizing Python, Streamlit, and AssemblyAI to translate spoken English with other languages in real time while offering a live demo
Orator is an adaptive voice coach: practice speaking, debating, or interviewing; get measured feedback, retry, and watch the system assign your next drill based on your weakest skill. Built on AssemblyAI streaming.
Ghostchain Command Hub is an autonomous AI multi-agent platform bridging cloud backends with mobile terminals to execute real-time production workflows and automated crypto earning strategies.