Methods

init(option: object): Promise

duix.init({
  sign: '',
  containerLable: '.remote-container'   
})

Parameters

Name	Type	Required	Description
containerLable	string	Yes	Digital human container. The digital human will be rendered in this DOM.
sign	string	Yes	Authentication string. How to get sign?

start(option:object): Promise

Calling the start method will begin rendering the digital human and initiate interaction.

Note: This method needs to be called after the intialSucccess event is triggered. The intialSucccess event indicates that all resources are prepared. As follows:
duix.on('intialSucccess', () => {
  duix.start({
     conversationId: '',    
     muted: true,
     wipeGreen: false,
 }).then(res => {
    console.log('res', res)
 })
})

Parameters

key	Type	Required	Default	Description
conversationId	number	Yes		Platform conversation id
muted	boolean	No	false	Whether to start the digital human video in muted mode. Important note: Due to autoplay policy restrictions, if your webpage has not had any click interaction with the user yet, please set this parameter to `true`, otherwise it will cause the digital human to fail to load. If you have such a requirement, it is recommended that you start in mute mode first, and design an interaction in your product, such as a “Start” button to call `duix.setVideoMuted(false)`
openAsr	boolean	No	false	Whether to directly enable real-time recognition. If this is set to true, it is equivalent to calling the `openAsr` method immediately after calling start
wipeGreen	boolean	No	false	Whether to perform green screen removal on the video. When creating a session on the platform, a pure green background image needs to be uploaded
userId	number	No		User unique identifier

setVideoMuted(flag:boolean)

Set whether the digital human video is muted, true is muted, false is unmuted.

break()

Interrupt the digital human speaking

speak(option: Object): Promise

Drive the digital human to speak, supporting text-driven and audio file-driven modes.

duix.speak({content: '', audio: 'https://your.website.com/xxx/x.wav'})

Parameters

Name	Type	Required	Description
content	string	Yes	Text for the digital human to answer
audio	string	No	Digital human answer audio address, which can be obtained through `getAnswer` to get the platform-configured answer
interrupt	boolean	No	Whether to interrupt the previous speech

answer(option: Object): Promise

Digital human answers a question

duix.answer({question: 'xxx'})

Parameters

Name	Type	Required	Description
question	string	Yes	Question text
interrupt	boolean	No	Whether to interrupt the previous speech

getAnswer(option: Object): Promise

Get the answer to a question from the platform

duix.getAnswer({ question: 'what is your name?' })

Parameters

Name	Type	Required	Description
question	string	Yes	Question text
userId	number	No	Business-side user unique ID, if specified, the obtained answer will have memory function enabled

Return data

Name	Type	Description
answer	string	Text answered by the digital human
audio	string	Digital human answer audio address

startRecord():Promise

Start recording.

stopRecord():Promise

End recording. After successful recording, it will return the speech recognition result (text) and return a Promise.

openAsr():Promise

Enable real-time speech recognition (note that this method needs to be called when the show event is triggered). After enabling real-time speech recognition, you can monitor the asrResult event to receive recognition (text) results.

closeAsr():Promise

Close real-time speech recognition.

stop()

Stop the current session. It is recommended to call this method in the page unload event to prevent resources from not being released in time when refreshing or closing the webpage.

window.addEventListener('beforeunload', function(event) {
  if (duix) {
    duix.stop()
  }
});

getLocalStream()

Get the local audio stream, which is convenient for external audio visualization and other functions

getRemoteStream()

Get the remote audio and video stream, which is convenient for external customization

resume()

Resume playback, currently only for some mobile browsers where even if autoplay is triggered by user operation, it still doesn’t work. Triggering the resume method through user operation in the 4009 error can solve this.

on(eventname, callback)

Listen for events.

Parameters

eventname

Event name, see the table below for details.

callback

Callback function

Return Format Description

For methods that return Promise, the parameter format is { err, data }. If err is not empty, it means the call failed.

API Documentation

Replica

Conversational Video Interface

iOS SDK

Android SDK

H5 SDK

init(option: object): Promise

start(option:object): Promise

setVideoMuted(flag:boolean)

break()

speak(option: Object): Promise

answer(option: Object): Promise

getAnswer(option: Object): Promise

startRecord():Promise

stopRecord():Promise

openAsr():Promise

closeAsr():Promise

stop()

getLocalStream()

getRemoteStream()

resume()

on(eventname, callback)

Parameters

eventname

callback

Return Format Description

​init(option: object): Promise

​start(option:object): Promise

​setVideoMuted(flag:boolean)

​break()

​speak(option: Object): Promise

​answer(option: Object): Promise

​getAnswer(option: Object): Promise

​startRecord():Promise

​stopRecord():Promise

​openAsr():Promise

​closeAsr():Promise

​stop()

​getLocalStream()

​getRemoteStream()

​resume()

​on(eventname, callback)

Parameters

eventname

callback

​Return Format Description

init(option: object): Promise

start(option:object): Promise

setVideoMuted(flag:boolean)

break()

speak(option: Object): Promise

answer(option: Object): Promise

getAnswer(option: Object): Promise

startRecord():Promise

stopRecord():Promise

openAsr():Promise

closeAsr():Promise

stop()

getLocalStream()

getRemoteStream()

resume()

on(eventname, callback)

Return Format Description