Neil Dwyer

Also seeing this for a headless linux build. Adding this comment to help inform priority. Thanks!

Haven't had this issue on chrome + macbook. WebRTC echo cancellation is typically pretty good. What browser/device are you testing on?

most likely related to: https://github.com/livekit/agents/issues/305 Re: OpenAI TTS. Streaming is supported with our StreamAdapter class. Examples coming soon

By the looks of it, your elevenlabs seems to be working properly (i.e. producing audio data) but you can't hear it? Can you share which versions of everything you're running?...

Which price tier of 11 labs are you using? Looks like they changed things up an PCM is only supported for pro tier: https://elevenlabs.io/docs/api-reference/streaming

Thanks for investigating and finding the cause. Closing this issue and adding a ticket on our end to make sure we have either sane defaults/or required params for this path.

@vanics it's a bit easier to tell the agent to stop than it telling it when to join. Using our server api sdk, you can send a data channel message...

We will soon be introducing an update where you can register track callbacks before the room is connected. There is currently a race condition where you could miss track subscription...

I've removed agent_status from the Playground UI here: https://github.com/livekit/agents-playground/pull/58 because it causes confusion. The above issues, like @Tails found, are likely due to elevenlabs, openai, or deepgram api keys/credits. @technoligest...

This should no longer be an issue: - ElevenLabs now supports long running ws connections along with a flush API - Our VoiceAssistant creates new streams for each response