DriveSafe.ly

Screenshots Goal The goal of this project was to help prevent people from driving dangerously by reading text messages to them and allowing them to respond with their voice. Implementation The app uses the iSpeech api to recognize the user’s voice and to speak any texts or emails the user receives. Completed The app accomplishes the stated goals and is being maintained. [Read More]

iSpeech-Speech-Recognition-ASR-Voice-Recognition.js

Goal This SDK is designed to enable developers to interact with the Voice Recognition iSpeech API using Javascript. Implementation The SDK uses getUserMedia() to record audio from the browser, encodes it to speex, then streams the data to the iSpeech API using a WebSocket. Completed This project completed the stated goals. My contribution I developed and maintained this project through its lifecycle, along with providing tech support where needed. [Read More]

iSpeech-Android-SDK

Goal The goal of this project was to create an open source Android SDK to help customers access the API quickly and easily. Implementation For Speech Recognition the SDK uses the Android system to record WAV audio, converts it to Speex, and streams that audio to the server in real time for recognition. For Text to Speech the SDK accesses iSpeech’s REST api and streams the audio. Completed The SDK accomplishes the stated goals and is being maintained. [Read More]