Discussions
Interactive Avatars and Knowledge base
I have been looking around to try and find some information about how the knowledge base actually work.
The demo shown here: https://labs.heygen.com/interactive-avatar?tab=public (click on the "+ Create New" button), just shows a field to enter a URLs. How about PDFs or documents or reports, etc.
Embedding Streaming SDK in WordPress with a Custom Script
Hello, I hope you're doing well. I'm using the "Create a Vite Project with Streaming SDK" demo, and our project is almost ready. However, we’d like to generate an embeddable script, similar to the one you provide, so we can easily integrate it into our WordPress website. My question is: How can I create a script from my demo to embed it in WordPress, ensuring the interactive avatar works correctly on the site? Are there any specific configurations or recommendations to achieve this? Thank you in advance for your help!
Avatar talking message event sends data but interactvie avatar is not speaking after the first speak request.
Hey,
I wanted to highlight minor but still important issue.
We're using Interactive avatar for voice chats. And we wanted avatar speaks first, so we send initial request to him:
knowledge base programmatically
We are using Interactive Avatar service on our side. We would like to check possibility to enhance our knowledge base programmatically.
By that - we mean that we should be able to expand our knowledge base information in HeyGen by using API calls which will keep updating KB with upto date information.
Custom Knowledge ID: where do I get this?
Hi. I got the NextJS demo project working (some dependencies are broken so it took a while) and can view the demo on http://localhost:3000
Problem with Speech-To-Text
Hi there,
I am using the heygen streaming-avatar 2.0.10 library in VoiceChat mode when working with an interactive avatar in React.
I have a problem with voice recognition which is as follows.
For example if I say the following text: “I'm sure that speaking aloud helps you.”
As a result of recognition I get in : “Iam surethat speaking aloudhelps you.”
This problem is quite often repeated in a conversation.
Important 3 questions
- What is the maximum allowed interaction time with an avatar? If it is static, how can this be configured while creating the session? Please provide the exact limits for both free and paid accounts.
- How can the session be terminated if a user closes the window while the session is being created?
- How can we set a session timeout for a static avatar when there is no interaction for a specific duration?
all this question are realated to realtime avatar sdk
can you please help me with this questions
Customizing the interactive avatar
Integrated the new interactive avatar using the suggested html code. Can the default language be changed to something else than English, and can the text of the button be changed from "Chat now" to something else? How?
Does enpodint, which creates webm videos, support callbacks?
I noticed that https://docs.heygen.com/reference/create-a-webm-video doesn't mention how to pass a callback_id. Does the https://api.heygen.com/v1/video.webm endpoint support this?
Make integration
While integrating heygen with MAKE workflow tool, how do i add a support for captions from the create video api triggered during the workflow execution. There does exist an option for enabling caption, which enables the default caption, but i am looking to generate a video with captions from the available list of caption styles available on the dashboard section.