SFSpeechRecognizer for iOS →

There's a lot of good stuff in this What's New in iOS 10 document. One thing of note, though, is there is now an API to easily initiate a speech to text session programmatically:

iOS 10 introduces a new API that supports continuous speech recognition and helps you build apps that can recognize speech and transcribe it into text.

Relevant sample code:

let recognizer = SFSpeechRecognizer()
let request = SFSpeechURLRecognitionRequest(url: audioFileURL)
recognizer?.recognitionTask(with: request, resultHandler: { (result, error) in
     print (result?.bestTranscription.formattedString)
})

Not as amazing as the SiriKit API offered up to certain categories of app, but could be really nice while we wait for that list of supported categories to grow.