# Gpt realtime transcription misses

**URL:** <https://community.livekit.io/t/gpt-realtime-transcription-misses/1456>\
**Category:** Getting Started\
**Created:** [June 18, 2026, 1:58pm UTC](https://community.livekit.io/t/gpt-realtime-transcription-misses/1456 "2026-06-18T13:58:03Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![AI\_Arjun](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/ai_arjun/32/241_2.png) [@AI\_Arjun](https://community.livekit.io/u/AI_Arjun)\
**Post date:** [June 18, 2026, 1:58pm UTC](https://community.livekit.io/t/gpt-realtime-transcription-misses/1456/1 "2026-06-18T13:58:04Z")

</div>

Hey for the folks using gpt realtime api for their agents, do you guys face an issue where the text generated by the model along with the audio misses at times.  
That is, in frontend the transcript misses being shown, but the audio is completely spoken out by the agent.

---

<div class="post-metadata">

**Author:** ![Pawel\_Lach](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/pawel_lach/32/1127_2.png) [@Pawel\_Lach](https://community.livekit.io/u/Pawel_Lach)\
**Post date:** [June 18, 2026, 2:03pm UTC](https://community.livekit.io/t/gpt-realtime-transcription-misses/1456/2 "2026-06-18T14:03:32Z")

</div>

As far as I know with the GPT real-time you cannot see the exact text that model understand, it’s rather some sort of STT model running in parallel like whisper for example, there for there may be discrepancy between what model actually hear and what is transcribed.

---

<div class="post-metadata">

**Author:** ![system](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/system/32/26_2.png) [@system](https://community.livekit.io/u/system)\
**Post date:** [July 3, 2026, 2:03pm UTC](https://community.livekit.io/t/gpt-realtime-transcription-misses/1456/3 "2026-07-03T14:03:57Z")

</div>

This topic was automatically closed 15 days after the last reply. New replies are no longer allowed.