Discussions
How to implement language translation?
I am using interactive avatar. I have an option to choose different language while starting a session.
Failed to initialize avatar after creating token in streaming API
Failed to initialize avatar after creating token below error occurs
Failed to load resource: the server responded with a status of 400 () https://api.heygen.com/v1/streaming.new
Failed to initialize an avatar session after the
main.ts:202
POST https://api.heygen.com/v1/streaming.new 400 (Bad Request)
initializeAvatarSession @ main.ts:202
await in initializeAvatarSession
handleConnectClick @ CourseContent.js:337
await in handleConnectClick
(anonymous) @ CourseContent.js:257
setTimeout
$ReactRefreshModuleRuntime$ @ CourseContent.js:1432
./src/components/CourseContent.js @ CourseContent.js:1432
options.factory @ react refresh:6
webpack_require @ bootstrap:22
_requireSelf @ hot module replacement:101
apply @ jsonp chunk loading:441
(anonymous) @ hot module replacement:341
internalApply @ hot module replacement:339
(anonymous) @ hot module replacement:277
waitForBlockingPromises @ hot module replacement:232
(anonymous) @ hot module replacement:275
Promise.then
(anonymous) @ hot module replacement:274
Promise.then
(anonymous) @ hot module replacement:255
Promise.then
hotCheck @ hot module replacement:246
Api Rate Limits, Latency, Scalability
Hi team,
An error occurs while attempting to upload an image asset to the API endpoint.
Endpoint: https://upload.heygen.com/v1/asset
How to Reduce Initial Latency (8-9s) in Assistants API with File Retrieval while Maintaining Full Retrieval Functionality
We're building a virtual university advisor where maintaining accurate, knowledge-based responses is crucial. Our main goal is to keep the full retrieval functionality but significantly reduce the initial response latency.
bypass built-in voice mode response with elevenlabs
Hi, im trying to integrate elevenlabs voice and response to bypass the built-in voice mode response of interactive avatar, how it could be possible? Which function handles this basic response?
Interactive Avatar in Android TV (Webview)
Hello,
Interactive Avatar Knowledge - Newby Question
Is is possible for the LLM to get its knowledge from a folder that contains text documents rather than the URL of a website ? or can the URL address be the folder location ?
Sawtooth Integration of Heygen
We have integrated API using Streaming API v2 Integration with LiveKit since we need to use it in Sawtooth and require raw files. Here’s the reference link:
Streaming API Integration with LiveKit v2
Below are two questions can you please response we can plan next step accordingly
1- Can we use replace-text-in-template with the Streaming API v2 Integration (LiveKit), as we have implemented HeyGen using this method?
2- If we need to integrate the SDK, can we implement it in JavaScript?