The Bing Speech Recognition API provides cloud based spoken language analysis and processing. Developers can integrate real time audio recognition via microphone or by sending the audio extracted from a file to the server. Additionally, this API converts spoken audio to intent as supported by the models trained by the Microsoft Language Understanding Intelligent Service (LUIS). 3 pricing options are available, and a free plan that limits transactions to 5,000 a month is available as well. The Speech Recognition API uses JSON format for data exchange, and Tokens for authentication.
In this, developer-blogger Alex Kras shows us how to overcome the 60 second audio file limitation of the free tier of Google's Cloud Speech API by taking a longer audio file, breaking it up into short chunks, and then cycling through those chunks to make a complete transcription.
A whopping Thirty Two APIs have been added to the ProgrammableWeb directory in the last few days in categories including Machine Learning, Sentiment, Payments, and Sports, among others. Highlights include APIs from Microsoft, IBM Watson, Square, and W3C. Here's a rundown of the latest additions.