interfaces/speech-api.idl

// GENERATED CONTENT - DO NOT EDIT
// Content was automatically extracted by Reffy into webref
// (https://github.com/w3c/webref)
// Source: Web Speech API (https://webaudio.github.io/web-speech-api/)

[SecureContext, Exposed=Window]
interface SpeechRecognition : EventTarget {
    constructor();

    // recognition parameters
    attribute SpeechGrammarList grammars;
    attribute DOMString lang;
    attribute boolean continuous;
    attribute boolean interimResults;
    attribute boolean unspokenPunctuation;
    attribute unsigned long maxAlternatives;
    attribute boolean processLocally;
    attribute ObservableArray<SpeechRecognitionPhrase> phrases;

    // methods to drive the speech interaction
    undefined start();
    undefined start(MediaStreamTrack audioTrack);
    undefined stop();
    undefined abort();
    static Promise<AvailabilityStatus> available(SpeechRecognitionOptions options);
    static Promise<boolean> install(SpeechRecognitionOptions options);

    // event methods
    attribute EventHandler onaudiostart;
    attribute EventHandler onsoundstart;
    attribute EventHandler onspeechstart;
    attribute EventHandler onspeechend;
    attribute EventHandler onsoundend;
    attribute EventHandler onaudioend;
    attribute EventHandler onresult;
    attribute EventHandler onnomatch;
    attribute EventHandler onerror;
    attribute EventHandler onstart;
    attribute EventHandler onend;
};

enum SpeechRecognitionQuality {
  "command",
  "dictation",
  "conversation"
};

dictionary SpeechRecognitionOptions {
  required sequence<DOMString> langs;
  boolean processLocally = false;
  SpeechRecognitionQuality quality = "command";
};

enum SpeechRecognitionErrorCode {
    "no-speech",
    "aborted",
    "audio-capture",
    "network",
    "not-allowed",
    "service-not-allowed",
    "language-not-supported",
    "phrases-not-supported"
};

enum AvailabilityStatus {
    "unavailable",
    "downloadable",
    "downloading",
    "available"
};

[SecureContext, Exposed=Window]
interface SpeechRecognitionErrorEvent : Event {
    constructor(DOMString type, SpeechRecognitionErrorEventInit eventInitDict);
    readonly attribute SpeechRecognitionErrorCode error;
    readonly attribute DOMString message;
};

dictionary SpeechRecognitionErrorEventInit : EventInit {
    required SpeechRecognitionErrorCode error;
    DOMString message = "";
};

// Item in N-best list
[SecureContext, Exposed=Window]
interface SpeechRecognitionAlternative {
    readonly attribute DOMString transcript;
    readonly attribute float confidence;
};

// A complete one-shot simple response
[SecureContext, Exposed=Window]
interface SpeechRecognitionResult {
    readonly attribute unsigned long length;
    getter SpeechRecognitionAlternative? item(unsigned long index);
    readonly attribute boolean isFinal;
};

// A collection of responses (used in continuous mode)
[SecureContext, Exposed=Window]
interface SpeechRecognitionResultList {
    readonly attribute unsigned long length;
    getter SpeechRecognitionResult? item(unsigned long index);
};

// A full response, which could be interim or final, part of a continuous response or not
[SecureContext, Exposed=Window]
interface SpeechRecognitionEvent : Event {
    constructor(DOMString type, SpeechRecognitionEventInit eventInitDict);
    readonly attribute unsigned long resultIndex;
    readonly attribute SpeechRecognitionResultList results;
};

dictionary SpeechRecognitionEventInit : EventInit {
    unsigned long resultIndex = 0;
    required SpeechRecognitionResultList results;
};

// The object representing a speech grammar. This interface has been deprecated and exists in this spec for the sole purpose of maintaining backwards compatibility.
[Exposed=Window]
interface SpeechGrammar {
    attribute DOMString src;
    attribute float weight;
};

// The object representing a speech grammar collection. This interface has been deprecated and exists in this spec for the sole purpose of maintaining backwards compatibility.
[Exposed=Window]
interface SpeechGrammarList {
    constructor();
    readonly attribute unsigned long length;
    getter SpeechGrammar? item(unsigned long index);
    undefined addFromUri(DOMString src,
                    optional float weight = 1.0);
    undefined addFromString(DOMString string,
                    optional float weight = 1.0);
};

// The object representing a phrase for contextual biasing.
[SecureContext, Exposed=Window]
interface SpeechRecognitionPhrase {
    constructor(DOMString phrase, optional float boost = 1.0);
    readonly attribute DOMString phrase;
    readonly attribute float boost;
};

[Exposed=Window]
interface SpeechSynthesis : EventTarget {
    readonly attribute boolean pending;
    readonly attribute boolean speaking;
    readonly attribute boolean paused;

    attribute EventHandler onvoiceschanged;

    undefined speak(SpeechSynthesisUtterance utterance);
    undefined cancel();
    undefined pause();
    undefined resume();
    sequence<SpeechSynthesisVoice> getVoices();
};

partial interface Window {
    [SameObject] readonly attribute SpeechSynthesis speechSynthesis;
};

[Exposed=Window]
interface SpeechSynthesisUtterance : EventTarget {
    constructor(optional DOMString text);

    attribute DOMString text;
    attribute DOMString lang;
    attribute SpeechSynthesisVoice? voice;
    attribute float volume;
    attribute float rate;
    attribute float pitch;

    attribute EventHandler onstart;
    attribute EventHandler onend;
    attribute EventHandler onerror;
    attribute EventHandler onpause;
    attribute EventHandler onresume;
    attribute EventHandler onmark;
    attribute EventHandler onboundary;
};

[Exposed=Window]
interface SpeechSynthesisEvent : Event {
    constructor(DOMString type, SpeechSynthesisEventInit eventInitDict);
    readonly attribute SpeechSynthesisUtterance utterance;
    readonly attribute unsigned long charIndex;
    readonly attribute unsigned long charLength;
    readonly attribute float elapsedTime;
    readonly attribute DOMString name;
};

dictionary SpeechSynthesisEventInit : EventInit {
    required SpeechSynthesisUtterance utterance;
    unsigned long charIndex = 0;
    unsigned long charLength = 0;
    float elapsedTime = 0;
    DOMString name = "";
};

enum SpeechSynthesisErrorCode {
    "canceled",
    "interrupted",
    "audio-busy",
    "audio-hardware",
    "network",
    "synthesis-unavailable",
    "synthesis-failed",
    "language-unavailable",
    "voice-unavailable",
    "text-too-long",
    "invalid-argument",
    "not-allowed",
};

[Exposed=Window]
interface SpeechSynthesisErrorEvent : SpeechSynthesisEvent {
    constructor(DOMString type, SpeechSynthesisErrorEventInit eventInitDict);
    readonly attribute SpeechSynthesisErrorCode error;
};

dictionary SpeechSynthesisErrorEventInit : SpeechSynthesisEventInit {
    required SpeechSynthesisErrorCode error;
};

[Exposed=Window]
interface SpeechSynthesisVoice {
    readonly attribute DOMString voiceURI;
    readonly attribute DOMString name;
    readonly attribute DOMString lang;
    readonly attribute boolean localService;
    readonly attribute boolean default;
};