Discussions

The main page UI allows custom audio and the update post says it's supported, but the API reference has voice_id and script as required fields and doesn't show any fields for custom audio.

I'm creating video avatars and I want them to look more natural, but they don't look realistic yet. I'm generating these videos using N8N, so I need help or a guide on how to improve the realism.

I'm trying to use the Streaming API integration with LiveKit V2 as per the official docs
, but it’s not working on localhost.
Even a simple HTML example gets stuck and the video doesn’t play properly.
Tested on multiple devices, same issue.
Any suggestions or fixes?

I can not find API to create my voice or import it from ElevenLabs.

I’m currently testing the Interactive Avatar and I’ve noticed an issue that keeps repeating. The avatar launches correctly, and I can start a conversation without any problem. However, after a while the avatar freezes and stops responding.

I’d like to integrate an interactive avatar into my Next.js website and allow users to select their preferred language before starting. What’s the best approach to implement this? Do you have any code samples? Also, which speech-to-text (STT) engine would you recommend to support Hindi and other Indian languages?

I've had an app hosted on Railway for two months without any problems: Public Avatar and voice.

In the streaming avatar API, using the task type of 'Chat'. has stopped working. The task type of 'repeat' still works. Please let me know if you or any other users are seeing the same issue as me.