Last month, we partnered with developer community hub Dev.to to host a winter hacking challenge! The competition saw great participation—75 people submitted projects across the following three categories:
- Build a sophisticated Speech-to-Text application with AssemblyAI’s latest Speech-to-Text model, Universal-2.
- Build a real-time Speech-to-Text application using AssemblyAI’s Streaming Speech-to-Text API.
- Build an LLM-powered feature on top of speech data using AssemblyAI’s LeMUR.
Participants were competing for the chance at a $1,000 prize and six month Dev++ membership, as well as exclusive gifts.
Submitted projects were judged on the following criteria:
- Use of underlying technology
- Usability and user experience
- Accessibility
- Creativity
Our team really enjoyed reviewing all the great projects and thank everyone for participating!
The winning projects are featured below:
Winner: Universal-2 Speech-to-Text
Insightview, created by Giovanni Improta, won for best use of Universal-2 Speech-to-Text.
According to Improta, Insightview is a modern web application that streamlines the interview workflow for journalists.
Leveraging both AssemblyAI's LeMUR and Universal-2 technology, it transforms raw interview recordings into structured, actionable content, dramatically reducing the time from recording to publication.
Key features of the application include:
- Audio/video file upload with real-time preview
- Advanced transcription with speaker identification
- Automatic highlight extraction of key moments
- AI-powered article draft generation
- Export interview's subtitles in VTT format
Winner: Streaming Speech-to-Text
BinaryGarage won the Streaming Speech-to-Text category for their application SpeechCraft—an AI-powered speech analysis assistant for better communication.
According to BinaryGarage, SpeechCraft is an advanced real-time speech analytics platform that transforms spoken words into actionable insights. Using cutting-edge AI technology from AssemblyAI, it provides instant transcription while analyzing multiple dimensions of speech performance.
Key features include:
- Real-time transcription
- Advanced speech metrics, including speaking pace analysis, clarity measurement, fluency assessment, speech rhythm, and vocabulary analysis.
- Visual analytics
Winner: LLM-powered application
Finally, Diosamual won the LLM-powered application category with ReportSOS: AI-powered SOS Emergency Caller.
According to Diosamual, with ReportSOS, emergencies get sorted faster and smarter. The app lets users report incidents in just a few taps, providing crucial details like location, type of emergency, and even summaries. It’s like giving dispatchers a superpower—cutting through the noise and delivering the right help to the right place, right on time.
Key features include:
- Voice recorder
- Location finder
- Dispatcher dashboard
