Chenghao Mou

There is a livekit plugin for ultravox now: https://pypi.org/project/livekit-plugins-ultravox/

I think for Chinese text, unlike English where words are separated by space, it is safe to use a lower ngram size such as 2 or 3. (Modify the ngram...

@cjmp1 Thank you so much for opening this issue. It does seem off based on your description. However, to effectively debug this discrepancy, could you provide 1) the commands you...

Thanks for providing the info. If you check out the union code, you can see that we are connecting parent index when calling union: ```python def union(self, x, y): px...

Similar requests/questions e.g. #962 #1687 I think, the difference here is that Livekit integration is primarily with TTS services/vendors, not TTS models. One can already easily create a new TTS...

Not tested, but I think they just [added](https://github.com/googleapis/python-genai/commit/807f098dedd0f885147fb10db7f79af9230999e0#diff-4579dd94816924284e59f28c7f6f42cab6c1389680a48da9b7f037a501890ce7) language code in speech config:

Also seeing the same issue. A workaround I found: filter requests with a custom `request_fnc` ```python seen = set() async def request_fnc(req: JobRequest): if req.room.name != room_id or req.room.name in...