J.A.R.V.I.S. Java Speech API: Just A Reliable Vocal Interpreter & Synthesizer. The program interprets vocal inputs into text and synthesizes voices from text input. The program supports dozens of languages and even has the ability to auto-detect languages. I started this project in high school, and made my first release in January of 2012, my sophomore year of high school. It originally started as a personal project, with the work done individually by me. I was trying to solve the problem of a lack of a good speech to text program library for the Java programming language. At this time, Google had released their own speech to text engine, and it was leaps and bounds ahead of anything in the market. I wanted to harness the power of this tool, and allow it to be usable by anyone in the world who programmed in Java. Essentially, this project is a library that allows anyone who programs to make their own applications that include Google’s speech recognition and synthesis.
When I first started the project, it supported only basic speech recognition and synthesis. However, because I released the project as an open-source project online, it gained popularity and soon other developers were joining the project. Around 2013, my junior year of high school, I started to collaborate with developers around the world to make the project even better than before. Through the efforts of other developers, the project grew and soon included many complex features, such as passive listening, translation, and more. The project is still being worked on today in 2016, almost four years later, by other developers who are interested in the project. It has achieved popularity as a competitor to other solutions in Java for speech recognition, with over 1,000 downloads for the API.
Link to the project and code: https://github.com/lkuza2/java-speech-api