# Inquiries about multilingualism in RTMS

**URL:** <https://devforum.zoom.us/t/inquiries-about-multilingualism-in-rtms/137162>\
**Category:** Realtime Media Streams\
**Created:** [September 7, 2025, 11:39pm UTC](https://devforum.zoom.us/t/inquiries-about-multilingualism-in-rtms/137162 "2025-09-07T23:39:03Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![hochoel](https://avatars.discourse-cdn.com/v4/letter/h/7ba0ec/32.png) [@hochoel](https://devforum.zoom.us/u/hochoel)\
**Post date:** [September 7, 2025, 11:39pm UTC](https://devforum.zoom.us/t/inquiries-about-multilingualism-in-rtms/137162/1 "2025-09-07T23:39:03Z")

</div>

I’m conducting a meeting in Korean, but for a while after the RTMS connection, the text is only delivered in English, and then at some point it’s delivered in Korean. I think it’s probably the moment when the model identifies the language and switches, but is there any way to specify it as Korean from the beginning? And because we’re an IT company, we often speak English as well, but when the model switches to Korean, it forces the English to be displayed in Korean. Is there any way to solve this? Real-time subtitles are much better.

---

<div class="post-metadata">

**Author:** ![chunsiong.zoom](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/chunsiong.zoom/32/35488_2.png) [@chunsiong.zoom](https://devforum.zoom.us/u/chunsiong.zoom)\
**Post date:** [September 9, 2025, 7:39am UTC](https://devforum.zoom.us/t/inquiries-about-multilingualism-in-rtms/137162/2 "2025-09-09T07:39:14Z")

</div>

@hochoel ,

Currently the detection of language is automatic. It will take around 10 seconds to detect the spoken language before the detected language and transcript will be available.

We are aware of this constrain, and will be look at this feature improvement