Chenghao Mou

Thanks for opening the issue. Unfortunately, there isn't much I can do to fix the issue. Here are some reasons: 1. The lyric is matched via search, and just like...

You can refer to other repos such as [LiveTalking](https://github.com/lipku/LiveTalking) which implemented a streaming service on top of MuseTalk. Regarding reading audio content, you can just modify the `AudioProcessor.get_audio_feature` function to...

In the upcoming 1.0 `agents` release, you will be able to play audio in `say`: You can see the code in the `agents` repo under the `dev-1.0` branch.

> @ChenghaoMou it would be best to parse this properly in `line_from_stream` ( > > https://github.com/ricklupton/rmscene/blob/ffcc16ff40ad760df13bed081f913939a7a31ddd/src/rmscene/scene_stream.py#L403-L433 > ) -- (I think) > > Can you add a simple-as-possible test file...

There is a PR #44, but it is waiting for several other PRs. @Utopiah Meanwhile, you could try my branch to see if it solves your issue: ```bash uv run...

> Thanks. It does run but how can I then use this with `rmc`? > > PS: I feel that I install one package manager per Python program, just discovered...

It seems that a datasetdict `{train: [...], test:[...]}` was loaded instead of a dataset `[...]`. Could you share the command you used?

It would be cool to have an endpoint like `https://docs.livekit.io/agents/llm.txt`

> It would be cool to have an endpoint like `https://docs.livekit.io/agents/llm.txt` Here is a full version as of today from Firecrawl (600k+ characters): [llm.txt](https://github.com/user-attachments/files/19735181/llm.txt) You can remove a large chunk...

[Deepwiki](https://deepwiki.com/livekit/agents) has this repo indexed.