Tina Nguyen

Hello, thank you for your detailed analysis of this issue! We'd be grateful if you could make a PR for this and more than happy to take a look!

Hi, thank you for expressing your interest! We are actively working on improving multi-lingual support for the turn detector. We will keep your request for Polish support in mind!

Hi Marc, if my understanding of the situation is right, I believe you would be correct here: > This means that the first token from the LLM cannot be sent...

Hi @marctorsoc, I just double checked and in `1.3.0rc1` , we actually have[ `MetricsReport`](https://github.com/livekit/agents/blob/b53e8593e417bed41574a34f53c0c72e990480dc/livekit-agents/livekit/agents/llm/chat_context.py#L144) which will measure the latency from the time the user finishes speaking to when the agent...

Hi, have you configured your credentials including `LIVEKIT_API_KEY` and `LIVEKIT_API_SECRET`? A 401 error suggests that authorization failed

Apologies, I just realized that `/agent` was automatically appended to the URL. I don't think we support custom voices for TTS in our inference yet, so that may be a...

In the code snippet you posted, the setup is still the same (using strings to load in the models via inference). Could you try importing the plugins and using those?

Hi, we would be interested in a way to allow silent reasoning and responses analyzing the current conversation, but as of right now [this is the best way to do...

@longcw is correct, that is the expected behavior. Perhaps you could create a class that handles a `BackgroundAudioPlayer` object pertaining to a specific audio file. Then, this new class could...

Hi, what do you mean by _"nothing but just a backlog"_? Having a chat context in `AgentSession` is useful for multi-agent workflows, is it the case that when you update...