# Experiencing response latency

**URL:** <https://forum.convai.com/t/experiencing-response-latency/6168>\
**Category:** Character Intelligence\
**Tags:** question, conversation-issues\
**Created:** [May 12, 2026, 4:58pm UTC](https://forum.convai.com/t/experiencing-response-latency/6168 "2026-05-12T16:58:53Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Samuel\_Ionesi](https://yyz2.discourse-cdn.com/flex004/user_avatar/forum.convai.com/samuel_ionesi/32/7093_2.png) [@Samuel\_Ionesi](https://forum.convai.com/u/Samuel_Ionesi)\
**Post date:** [May 12, 2026, 4:58pm UTC](https://forum.convai.com/t/experiencing-response-latency/6168/1 "2026-05-12T16:58:53Z")

</div>

Hi,

I’m building a VR therapy application on Meta Quest 2 using Convai SDK v4.1.0  
with Unity 6 and URP. The app is running standalone on Quest 2 (Android build).

I’m experiencing response latency of around 4-6 seconds from when the patient  
speaks to when Delia (my AI character) starts responding. This is noticeable  
and affects the therapy experience.

My current setup:

- Model: gpt-4o-mini
- Core Description: ~600 words
- TTS: default Convai voice
- Platform: Meta Quest 2 standalone, WiFi connection
- SDK: Convai v4.1.0, Unity 6000.4.2f1

Questions:

1. Which LLM model gives the fastest response time for short conversational  
replies in Romanian?
2. Which TTS voice/engine has the lowest latency?
3. Does Core Description length significantly impact response time?
4. Are there any SDK-level settings to reduce latency  
(streaming, buffer size, etc.)?
5. Is there a recommended architecture for minimizing latency on  
standalone VR headsets?

Thank you!

---

<div class="post-metadata">

**Author:** ![K3](https://yyz2.discourse-cdn.com/flex004/user_avatar/forum.convai.com/k3/32/2611_2.png) [@K3](https://forum.convai.com/u/K3)\
**Post date:** [May 12, 2026, 5:33pm UTC](https://forum.convai.com/t/experiencing-response-latency/6168/2 "2026-05-12T17:33:12Z")

</div>

Hello,

Could you please try using GPT-Realtime 1.5 and let us know if the issue still occurs?

---

<div class="post-metadata">

**Author:** ![Samuel\_Ionesi](https://yyz2.discourse-cdn.com/flex004/user_avatar/forum.convai.com/samuel_ionesi/32/7093_2.png) [@Samuel\_Ionesi](https://forum.convai.com/u/Samuel_Ionesi)\
**Post date:** [May 12, 2026, 7:02pm UTC](https://forum.convai.com/t/experiencing-response-latency/6168/4 "2026-05-12T19:02:01Z")

</div>

Hi, I tried with GPT-Realtime 1.5 and it’s much better.

---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex004/uploads/convai/original/1X/e60ef96aa7334c5ccf6682f6c6dbc20fcfa96b49.png) [@system](https://forum.convai.com/u/system)\
**Post date:** [June 11, 2026, 7:02pm UTC](https://forum.convai.com/t/experiencing-response-latency/6168/5 "2026-06-11T19:02:37Z")

</div>

Closed on June 11, 2026, 7:02pm UTC

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.