SpeechRecognitionAlternative.confidence

This is an experimental technology
Check the Browser compatibility table carefully before using this in production.

The confidence read-only property of the SpeechRecognitionResult interface returns a numeric estimate of how confident the speech recognition system is that the recognition is correct.

Note: Mozilla's implementation of confidence is still being worked on — at the moment, it always seems to return 1.

Syntax

var myConfidence = speechRecognitionAlternativeInstance.confidence;

Returns

A number betwen 0 and 1.

Examples

This code is excerpted from our Speech color changer example.

recognition.onresult = function(event) {
  // The SpeechRecognitionEvent results property returns a SpeechRecognitionResultList object
  // The SpeechRecognitionResultList object contains SpeechRecognitionResult objects.
  // It has a getter so it can be accessed like an array
  // The first [0] returns the SpeechRecognitionResult at position 0.
  // Each SpeechRecognitionResult object contains SpeechRecognitionAlternative objects that contain individual results.
  // These also have getters so they can be accessed like arrays.
  // The second [0] returns the SpeechRecognitionAlternative at position 0.
  // We then return the transcript property of the SpeechRecognitionAlternative object
  var color = event.results[0][0].transcript;
  diagnostic.textContent = 'Result received: ' + color + '.';
  bg.style.backgroundColor = color;
  console.log('Confidence: ' + event.results[0][0].confidence);
}

Specifications

Specification	Status	Comment
Web Speech API The definition of 'confidence' in that specification.	Draft

Browser compatibility

	Desktop						Mobile
	Chrome	Edge	Firefox	Internet Explorer	Opera	Safari	Android webview	Chrome for Android	Firefox for Android	Opera for Android	Safari on iOS	Samsung Internet
`confidence` Experimental	Chrome Full support 33 Prefixed Notes Full support 33 Prefixed Notes Prefixed Implemented with the vendor prefix: webkit Notes You'll need to serve your code through a web server for recognition to work.	Edge Full support ≤79 Prefixed Notes Full support ≤79 Prefixed Notes Prefixed Implemented with the vendor prefix: webkit Notes You'll need to serve your code through a web server for recognition to work.	Firefox No support No	IE No support No	Opera No support No	Safari No support No	WebView Android Full support Yes Prefixed Notes Full support Yes Prefixed Notes Prefixed Implemented with the vendor prefix: webkit Notes You'll need to serve your code through a web server for recognition to work.	Chrome Android Full support Yes Prefixed Notes Full support Yes Prefixed Notes Prefixed Implemented with the vendor prefix: webkit Notes You'll need to serve your code through a web server for recognition to work.	Firefox Android No support No	Opera Android No support No	Safari iOS No support No	Samsung Internet Android Full support Yes Prefixed Notes Full support Yes Prefixed Notes Prefixed Implemented with the vendor prefix: webkit Notes You'll need to serve your code through a web server for recognition to work.

Legend

Full support: Full support
No support: No support
Experimental. Expect behavior to change in the future.: Experimental. Expect behavior to change in the future.
See implementation notes.: See implementation notes.
Requires a vendor prefix or different name for use.: Requires a vendor prefix or different name for use.

[1] Speech recognition interfaces are currently prefixed on Chrome, so you'll need to prefix interface names appropriately, e.g. webkitSpeechRecognition; You'll also need to serve your code through a web server for recognition to work.
[2] Can be enabled via the media.webspeech.recognition.enable flag in about:config, although note that currently speech recognition won't work on Desktop Firefox — it will be properly exposed soon, once the required internal permissions are sorted out.