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? |
conversationId | number | Yes | Platform conversation id |
platform | string | No | The platform type is duix.guiji.ai by default. If it is for overseas users to connect, it is duix.com |
start
method will begin rendering the digital human and initiate interaction.
Note: This method needs to be called after theParametersinitialSuccess
event is triggered. TheinitialSuccess
event indicates that all resources are prepared. As follows:
key | Type | Required | Default | Description |
---|---|---|---|---|
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 | |
vadSilenceTime | number | 否 | 800 | asr delay |
enableLLM | number | 否 | 1 | Whether to enable the large model’s automatic reply, 0 for off, 1 for on. |
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 |
Name | Type | Required | Description |
---|---|---|---|
question | string | Yes | Question text |
interrupt | boolean | No | Whether to interrupt the previous speech |
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 |
Name | Type | Description |
---|---|---|
answer | string | Text answered by the digital human |
audio | string | Digital human answer audio address |
asrResult
event to receive recognition (text) results.
Promise
, the parameter format is { err, data }
. If err
is not empty, it means the call failed.