Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
An open-source real-time captioning and translation platform for conferences, designed to make technical events accessible and scalable across multiple stages.
This project was built with many ai agents like qwen, gpt, kimi and deepseek in less than 24 hours as an MVP and im wiling to update it if the jury find it interesting. Opensource and proud of it
Every voice. Every language. Everyone included. EventLyra turns a live talk into open-source captions the whole room can follow, in real time.
Open-source, real-time AI transcription & translation platform for massive conferences. Powered by Gemini, featuring multi-stage support, gapless Web Audio, and seamless OBS integration.
Live captions with speaker names and per-language translation for multi-track conferences.
Subtítulos y traducción en vivo, abiertos y a escala.
Lenguaraz turns the audio of every stage of a conference into live captions, in the language being spoken and translated into the languages the audience asks for.
Subtitulado y traducción en tiempo real para conferencias: 32+ salas simultáneas en 8 idiomas con latencia <12ms, impulsado por Gemini Live y Gemma 4.
Open source live captions and translation for conferences: every talk, subtitled on each attendee's phone in their own language in about 2 seconds, or read aloud through their headphones.
Cualquiera puede subtitular y traducir su conferencia en vivo: ejecutas un instalador, pegás una clave de Gemini y listo. Baja latencia, escala a toda la conferencia y cuesta centavos por charla.
Sistema para transcribir y traducir texto de las charlas de Nerdearla. Diseñado con escalabilidad y simultaneidad en mente
Open-source real-time multilingual captions and translation for live events.
Present in every word.
Subtítulos en vivo, self-hosted, para charlas de conferencias de tecnología: transcripción en el idioma original y traducción a español en tiempo real, corriendo 100% en tu propia infra.
Hay charlas buenísimas que te perdés porque no son en tu idioma. Subdearla las subtitula y traduce en vivo, en todas las salas a la vez, y convierte los mejores momentos en clips.
Subtítulos y traducción simultánea para conferencias: menos de un segundo de latencia, el audio se decodifica una sola vez por sala y el costo por idioma extra es casi cero
Alexa+ places the order. FrontDesk handles everything after: rider calls, OTP scams and booking changes, so you stay focused.
Pipeline Open Source automatizado: procesa audio en vivo con Gemini (o Gemma local) y traduce a ES/EN. Arquitectura event-driven que escala a 30+ charlas sin intervención humana.
Real-time transcription for live conferences. Simultaneous sessions, instant subtitles (original language + Spanish). Open source, zero cost, built for accessibility at scale.
Open-source live captions & translation for every room of a conference, plus "What did I miss?" summaries and "Ask the talk", in your language. Gemini-powered, zero-operator.
Open-source bilingual live captions that scale by stage, not by audience.
Te presento a Conffy - Tu Buddy de Conferencias - Subtítulos en vivo para cada escenario. Cada escenario transmite su audio, abrís una web, elegís la sala y ves los subtítulos en vivo en tu idioma.
Film yourself moving a cup. OpenCV 5 on AWS tracks it, a Franka Panda in MuJoCo repeats it, and a Claude agent checks the result with OpenCV, then retries, accepts, or asks a human. No teleop.
Open source live captions and translation for every stage of your conference, powered by Gemini Live. Tested: 10 stages, 0 errors, ~1 s.
